SENSE: State-aware Emotion Navigation Storytelling Engine

2026-10-05

AI Summary

This study addresses the challenge of simultaneously achieving narrative coherence and emotional richness in branching visual novel generation by proposing a state-aware framework. The framework integrates the MIND architecture, a structural analyzer, and a path-aware module, alongside a state-aware emotional navigation mechanism. By leveraging large language model-driven generation, state machine modeling, and context management techniques, it produces multi-track, interwoven, and character-consistent playable narratives from minimal input. Experimental results demonstrate that the proposed method outperforms baseline models in narrative diversity, asset integration, and emotional fidelity. Furthermore, human evaluations confirm significant improvements in user experience.

Abstract

This paper presents SENSE, a state-aware framework for generating playable branching visual novels with multi-track emotional navigation. Integrating a state-based narrative architecture called MIND, a structure analyzer, and a path-aware context management module, SENSE produces narratives that are both structurally coherent and emotionally rich. From minimal high-level inputs, it generates multiple intersecting routes while preserving character consistency and narrative causality. Evaluations using LLM judges, affective metrics, and visual assessments indicate SENSE outperforms baselines in narrative diversity and robust asset integration, while preliminary human trials show directional improvements in emotional fidelity alongside comparable enjoyment.

Problem

• visual novel generation
• branching narrative
• emotion navigation
• storytelling engine
• narrative coherence

Innovation

• State-aware Narrative
• Branching Visual Novels
• Emotion Navigation
• Path-aware Context Management
• Procedural Storytelling