# Large Emotional World Model

arXiv: https://arxiv.org/abs/2512.24149 · HTML: https://mlsanity.com/paper/2512.24149/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 14 of its 37 references that are in the map.
- First posted on arXiv 30 Dec 2025.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)

## Builds on (most cited first, 14 of 14)

- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations](https://mlsanity.com/paper/1810.02508/) (2018)
- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)
- [NExT-GPT: Any-to-Any Multimodal LLM](https://mlsanity.com/paper/2309.05519/) (2023)
- [Transformers are Sample-Efficient World Models](https://mlsanity.com/paper/2209.00588/) (2022)
- [Embodied AI Agents: Modeling the World](https://mlsanity.com/paper/2506.22355/) (2025)
- [EMO-LLaMA: Enhancing Facial Emotion Understanding with Instruction Tuning](https://mlsanity.com/paper/2408.11424/) (2024)
- [AffectGPT-R1: Leveraging Reinforcement Learning for Open-Vocabulary Multimodal Emotion Recognition](https://mlsanity.com/paper/2508.01318/) (2025)
- [ECR-Chain: Advancing Generative Language Models to Better Emotion-Cause Reasoners through Reasoning Chains](https://mlsanity.com/paper/2405.10860/) (2024)
- [Enhancing Large Language Model with Decomposed Reasoning for Emotion Cause Pair Extraction](https://mlsanity.com/paper/2401.17716/) (2024)
- [Emotion-o1: Adaptive Long Reasoning for Emotion Understanding in LLMs](https://mlsanity.com/paper/2505.22548/) (2025)

## Built on by (most cited first, 2 of 2)

- [Bridging the Agent-World Gap: Text World Models for LLM-based Agents](https://mlsanity.com/paper/2606.09032/) (2026)
- [The Bell Boundary of Shared Representations](https://mlsanity.com/paper/2610.16828/) (2026)

## Abstract (arXiv)

The world is governed by both physical laws and affective dynamics. Physical laws govern state transitions, while affective dynamics shape human actions, decisions, and interactions. A world model that learns only physical laws can approximate the physical world, but not the human world. In this paper, we introduce human emotion as a key state variable in world models, enabling them to capture both future state transitions and their emotional causes. We first construct Emotion-Why-How (EWH), the first world model dataset centered on emotional state transitions, containing 10,850 emotion-aware transition tuples. Each tuple encodes the pre-state, pre-emotion, action, post-emotion, and post-state, supporting reasoning about why actions occur and how emotions reshape future states. Based on EWH, we propose the Large Emotional World Model (LEWM), which factorizes future prediction into two coupled steps: first predicting the future emotional state from the current context, and then conditioning future world-state prediction on the predicted emotion. Experiments show that LEWM brings consistent gains across world-state prediction, emotion understanding, and general reasoning tasks. It achieves up to 45.72% accuracy improvement on EWH, 3.94% on WorldNet, 17.47% F1 improvement on MELD, and a 6.10% gain on specific MMLU categories. These results demonstrate that incorporating emotion into world models enables more realistic simulation of human-centered environments and expands the predictive understanding of intelligent agents.