# Are Emotion and Rhetoric Neurons in LLM? Neuron Recognition and Adaptive Masking for Emotion-Rhetoric Prediction Steering

arXiv: https://arxiv.org/abs/2604.17255 · HTML: https://mlsanity.com/paper/2604.17255/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning.
- Builds on 26 of its 51 references that are in the map.
- First posted on arXiv 19 Apr 2026.

## Placed in

- LLM reasoning / [Audio-language model reasoning](https://mlsanity.com/lr/audio-language-model-reasoning/)

## Builds on (most cited first, 26 of 26)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [Toward Controlled Generation of Text](https://mlsanity.com/paper/1703.00955/) (2017)
- [Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper)](https://mlsanity.com/paper/1906.01815/) (2019)
- [Learning to Generate Reviews and Discovering Sentiment](https://mlsanity.com/paper/1704.01444/) (2017)
- [Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves](https://mlsanity.com/paper/2311.04205/) (2023)
- [EmoLLMs: A Series of Emotional Large Language Models and Annotation Tools for Comprehensive Affective Analysis](https://mlsanity.com/paper/2401.08508/) (2024)
- [Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation](https://mlsanity.com/paper/2312.02439/) (2023)
- [Creating and Characterizing a Diverse Corpus of Sarcasm in Dialogue](https://mlsanity.com/paper/1709.05404/) (2017)
- [Metaphor Generation with Conceptual Mappings](https://mlsanity.com/paper/2106.01228/) (2021)
- [DialogBench: Evaluating LLMs as Human-like Dialogue Systems](https://mlsanity.com/paper/2311.01677/) (2023)
- [Mechanistic Interpretability of Emotion Inference in Large Language Models](https://mlsanity.com/paper/2502.05489/) (2025)
- [ColBERT: Using BERT Sentence Embedding in Parallel Neural Networks for Computational Humor](https://mlsanity.com/paper/2004.12765/) (2020)
- [InstructAvatar: Text-Guided Emotion and Motion Control for Avatar Generation](https://mlsanity.com/paper/2405.15758/) (2024)
- [LLaMAs Have Feelings Too: Unveiling Sentiment and Emotion Representations in LLaMA Models Through Probing](https://mlsanity.com/paper/2505.16491/) (2025)
- [Multi-Granular Multimodal Clue Fusion for Meme Understanding](https://mlsanity.com/paper/2503.12560/) (2025)
- [MOVER: Mask, Over-generate and Rank for Hyperbole Generation](https://mlsanity.com/paper/2109.07726/) (2021)
- [One Does Not Simply Meme Alone: Evaluating Co-Creativity Between LLMs and Humans in the Generation of Humor](https://mlsanity.com/paper/2501.11433/) (2025)
- [LLM-Friendly Knowledge Representation for Customer Support](https://mlsanity.com/paper/2510.10331/) (2025)
- [Zero-Shot Conversational Stance Detection: Dataset and Approaches](https://mlsanity.com/paper/2506.17693/) (2025)
- [Stimulating Creativity with FunLines: A Case Study of Humor Generation in Headlines](https://mlsanity.com/paper/2002.02031/) (2020)
- [Cultural Bias Matters: A Cross-Cultural Benchmark Dataset and Sentiment-Enriched Model for Understanding Multimodal Metaphors](https://mlsanity.com/paper/2506.06987/) (2025)
- [Reverse Multi-Choice Dialogue Commonsense Inference with Graph-of-Thought](https://mlsanity.com/paper/2312.15291/) (2023)
- [Enhancing Hyperbole and Metaphor Detection with Their Bidirectional Dynamic Interaction and Emotion Knowledge](https://mlsanity.com/paper/2506.15504/) (2025)
- [My Words Imply Your Opinion: Reader Agent-based Propagation Enhancement for Personalized Implicit Emotion Analysis](https://mlsanity.com/paper/2412.07367/) (2024)
- [Target-Augmented Shared Fusion-based Multimodal Sarcasm Explanation Generation](https://mlsanity.com/paper/2502.07391/) (2025)

## Abstract (arXiv)

Accurate comprehension and controllable generation of emotion and rhetoric are pivotal for enhancing the reasoning capabilities of large language models (LLMs). Existing studies mostly rely on external optimizations, lacking in-depth exploration of internal representation mechanisms, thus failing to achieve fine-grained steering at the neuron level. A handful of works on neurons are confined to emotions, neglecting rhetoric neurons and their intrinsic connections. Traditional neuron masking also exhibits counterintuitive phenomena, making reliable verification of neuron functionality infeasible. To address these issues, we systematically investigate the neurons representation mechanisms and inherent associations of 6 emotion categories and 4 core rhetorical devices. We propose a neuron identification framework that integrates multi-dimensional screening, and design an adaptive masking method incorporating dynamic filtering, attenuation masking, and feedback optimization, enabling reliable causal validation of neuron functionality.Through neuron regulation, we achieve directed induction of non-target sentences and enhancement of emotion tasks via rhetoric neurons. Experiments on 5 commonly used datasets validate the effectiveness of our method, providing a novel paradigm for the fine-grained steering of emotion and rhetoric expressions in LLMs.