goldtag

What It Means to Design Scenarios with AI From the moment my kid said "visual novel," we have come this far. Twenty parts. Looking back, we have covered quite a distance. Not a single line of code was written. Ren'Py was never installed. And yet the most important work of this project is done. Scenario design. The work of understanding the structure of emotion and translating it into systems. What I Discovered on This Journey At the start, the goal was "making a visual novel." By the end, the goal had shifted. Making a visual novel is not technically difficult. Ren'Py handles most of the technical challenges. The difficult part is making a visual novel that truly moves the player's emotions. And for that, what you need is not technology but an understanding of emotion. Love is not a single variable but the result of conditions. A scene is not a backdrop but an amplifier of emotion. The consequences of choices arrive not immediately but later. Good ...

What Happens When You Hand AI a Scenario Throughout this project, the area where I talked most with AI was scenario design. System architecture, character settings, conflict patterns, time structure. AI was used in every step. I want to leave an honest review. What AI does well, what it cannot do, and how to use it effectively. What AI Does Well Organizing structure. This is overwhelming. Say "I want to design an emotion system," and it immediately proposes a systematic variable structure with layer separation. Information organization that would take a person days is done in minutes. The skeleton of the three-layer emotion model came out within an hour of conversation with AI. Verifying consistency between variables. It answers logically to questions like "If trust goes up in this event, what should happen to tension?" When variables multiply, humans start missing things; AI does not. Presenting patterns. For requests like "Classify the types of confl...

Translating Emotion into Variables — The Three-Layer Emotion Model Now it's time to design emotion in earnest. Having identified the limits of Affection+1, we need to build a system to replace it. I told AI: "I don't want a single affection variable. I want a variable system that represents human emotion more realistically." And this is where AI really started showing its strength. Structuring emotion — decomposing something abstract into variables and layers — is exactly the kind of work AI excels at. How Many Emotions Do We Need? That was the first question. "How many emotion variables should we have?" AI's answer was surprisingly cautious. "More isn't always better. Too many variables leads to overengineering." Then it proposed a crucial distinction: The types of emotion you express can be many. But the state values the system directly tracks must be structurally organized. What does that mean? Love, sadness, anger, arrogance, env...

Is This a Limitation of Games, or of Design? So far, we've analyzed why visual novel emotions are special and how they differ from other media. We've confirmed that the visual novel genre has a structure well-suited for handling emotion. But most real-world visual novels don't use that potential fully. Many provide an experience closer to "walkthrough optimization" than genuine emotion. Why? AI and I dug into the structural problems of existing visual novels. The World of Affection+1 Most visual novels work like this: Choose option A, the character's affection rises by 1. Choose option B, affection stays the same or drops. Cross a threshold and you enter the romance route. Fall short and you get a bad or normal ending. This system is easy to implement. One variable, a few conditionals. Testing is simple. Balancing is intuitive. Low production cost means most visual novels adopt this structure. But this structure has fundamental problems. When I asked AI...

What If It Were a Film or Novel? To understand the emotional structure of visual novels, I needed a point of comparison. Other media that handle the same subject — relationships and emotions between people. Films and novels. I asked AI: "What's the difference in how films, novels, and visual novels each deliver emotion?" Then I combined the analysis with my own experience. Film: Emotion Under Time Control Film controls time. Within a fixed two hours, the director decides everything. How long to show a scene, when to bring in music, where the camera looks. The audience surrenders to the flow. This control is film's strength. At exactly the moment the director wants, they can produce exactly the emotion they intended. When the camera lingers on a character's eyes during a sad scene, the music swells, silence extends — the audience's emotions follow almost automatically. I think of Christmas in August. The emotion this film creates is "regret for what ...

Why Can't Other Games Draw Out Emotion? We've analyzed why emotion emerges in visual novels. The reverse question follows naturally: why can't other games do the same? Of course, "can't" is an overstatement. People have cried playing The Last of Us, felt their chest tighten in Final Fantasy. But those emotions mostly come from cutscenes or story events. It's rare for the gameplay itself to produce relationship emotions. Why? AI and I dug deep into this topic. Games' Basic Structure Clashes with Emotion Most games are built on a challenge-reward structure. Defeat enemies for experience, complete quests for rewards, clear stages to progress. The emotions this produces are achievement, tension, thrill. Intense, but different in texture from relationship emotions. Relationship emotions sit at the opposite end of efficiency. Liking someone is inefficient. Anxious, irrational, uncontrollable. The challenge-reward structure fundamentally conflicts with ...

Drawing Out Emotion in a Short Time In the previous entry, I said emotion is built by time. But there's a contradiction. A visual novel can't be infinitely long. Player time is finite. You need to generate real emotion from a character relationship within a few hours — a dozen at most. Films make people cry in two hours. Short stories leave lasting impressions in under ten thousand words. How do they do it? And what's the same and different about visual novels? The Concept of Emotional Density Discussing this topic with AI, one concept crystallized: Emotional Density. Emotional density is the concentration of emotional change a player experiences per unit of time. The same thirty minutes can feel entirely different depending on whether nothing happens or a decisive relationship moment unfolds. High density isn't always better. Sustained intensity creates fatigue. Sustained low density creates boredom. What matters is controlling the density — the rhythm. AI drew ...

Why Do People Play Visual Novels? My kid asked, "What happens if I pick something bad?" When I said "It might make you sad," they asked, "Why?" Why would it make you sad? The character on screen doesn't exist. The dialogue is text someone wrote in advance. The choices are just programmed branches. It's all fake — so why do the emotions feel real? This is a question that must be understood before building a visual novel. If you don't know why emotions occur, you can't design them. I Asked AI First "Why do people feel emotions in visual novels?" The question I threw at Claude. AI produced several keywords: parasocial relationships, self-projection, narrative immersion, player agency. The summary: Parasocial Relationship — A one-sided relationship that feels real. The same structure as feeling close to a TV celebrity. Visual novel characters fall into this category. Self-Projection — The player places themselves in the prot...

The Games I Used to Play After deciding to make a visual novel, something strange happened. Before looking into how to build one, the games I used to play surfaced first. To understand a genre, you analyze its structure. AI can handle that. But "why this genre pulls people in" isn't something analysis can answer. That was stored in memory. The First Visual Novel I Played I can't remember exactly when. Probably high school. On a friend's computer, or at my desk in my own room. There are games whose titles I can't quite recall. Games that would turn up with a search, probably. But it's not the titles that stuck — it's the feeling. I remember the setting was a school. Characters in a classroom. Lunch breaks. After-school hours. When a choice appeared, I'd pause and think. Which option would this character like? What dialogue would follow? I saved and loaded over and over, trying different choices. Looking back, it's almost laughable. Agonizi...

What Even Is a Visual Novel? Having decided to make a visual novel, I needed to actually understand what one is. Everyone has a rough idea of what a dating sim is, but if you ask "so what is it exactly?" the answer gets surprisingly vague. Dating simulation? Visual novel? Text adventure? Choice-based game? It's hard to tell whether these terms all point to the same thing or different things. If you're going to build something, you need to know exactly what you're building. Time to look it up. Let's Start with Terminology "What's the difference between a dating sim and a visual novel?" That was the first question I threw at Claude. Here's the summary. Visual Novel is a format. You read text, see background images and character illustrations, and encounter choices along the way. A game centered on the act of reading. There are plenty of visual novels that have nothing to do with romance — mystery, horror, sci-fi, slice of life. The conte...

My Kid Said They Wanted to Make a Game I'd started making games as a hobby. I'd previously completed a tarot project with AI, and a Four Pillars of Destiny (saju) project too. Both were substantial enough to warrant 20-part development diaries, and I'd gained confidence in AI-collaborative development. While thinking about what to tackle next, games caught my eye. A domain I'd never built for, but had plenty of experience playing. My developer curiosity was piqued. So I asked my kid. "Dad's been making games as a hobby lately. Do you have a game you'd like to make? We could build it together." Their eyes went wide. "Really? I can do it too?" "Sure. What kind of game do you like?" A moment of thought, then the answer: "A dating sim." I was caught off guard. I'd expected them to say a shooter, a puzzle game, maybe something like Minecraft. A dating sim? I have no idea where they picked that up — trending among fri...