# LLaMAs Have Feelings Too: Unveiling Sentiment and Emotion Representations in LLaMA Models Through Probing

arXiv: https://arxiv.org/abs/2505.16491 · HTML: https://mlsanity.com/paper/2505.16491/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 79 references that are in the map.
- First posted on arXiv 22 May 2025.

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [Is ChatGPT a General-Purpose Natural Language Processing Task Solver?](https://mlsanity.com/paper/2302.06476/) (2023)
- [Larger language models do in-context learning differently](https://mlsanity.com/paper/2303.03846/) (2023)
- [FinBERT: Financial Sentiment Analysis with Pre-trained Language Models](https://mlsanity.com/paper/1908.10063/) (2019)
- [Sentiment Analysis in the Era of Large Language Models: A Reality Check](https://mlsanity.com/paper/2305.15005/) (2023)
- [Probing Pretrained Language Models for Lexical Semantics](https://mlsanity.com/paper/2010.05731/) (2020)
- [TweetNLP: Cutting-Edge Natural Language Processing for Social Media](https://mlsanity.com/paper/2206.14774/) (2022)
- [Eliciting Latent Knowledge from Quirky Language Models](https://mlsanity.com/paper/2312.01037/) (2023)
- [Probing LLMs for hate speech detection: strengths and vulnerabilities](https://mlsanity.com/paper/2310.12860/) (2023)
- [Designing Heterogeneous LLM Agents for Financial Sentiment Analysis](https://mlsanity.com/paper/2401.05799/) (2024)
- [A Language Model's Guide Through Latent Space](https://mlsanity.com/paper/2402.14433/) (2024)
- [Probing the Emergence of Cross-lingual Alignment during LLM Training](https://mlsanity.com/paper/2406.13229/) (2024)
- [Towards Understanding In-Context Learning with Contrastive Demonstrations and Saliency Maps](https://mlsanity.com/paper/2307.05052/) (2023)
- [Transforming Sentiment Analysis in the Financial Domain with ChatGPT](https://mlsanity.com/paper/2308.07935/) (2023)
- [Zero- and Few-Shot Prompting with LLMs: A Comparative Study with Fine-tuned Models for Bangla Sentiment Analysis](https://mlsanity.com/paper/2308.10783/) (2023)

## Built on by (most cited first, 15 of 15)

- [Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry](https://mlsanity.com/paper/2601.22588/) (2026)
- [Eliciting Numerical Predictive Distributions of LLMs Without Autoregression](https://mlsanity.com/paper/2603.02913/) (2026)
- [Do Emotions Influence Moral Judgment in Large Language Models?](https://mlsanity.com/paper/2604.19125/) (2026)
- [How Tokenization Limits Phonological Knowledge Representation in Language Models and How to Improve Them](https://mlsanity.com/paper/2604.17105/) (2026)
- [Why Are Some Emotions Harder for LLMs? Uncovering the Causal Mechanisms of Emotion Inference via Sparse Autoencoders](https://mlsanity.com/paper/2604.25866/) (2026)
- [STEREODISCO: Discovering Stereotypicality in LLMs](https://mlsanity.com/paper/2607.27824/) (2026)
- [Exploring Diversity, Novelty, and Popularity Bias in ChatGPT's Recommendations](https://mlsanity.com/paper/2601.01997/) (2026)
- [Exploring Approaches for Detecting Memorization of Recommender System Data in Large Language Models](https://mlsanity.com/paper/2601.02002/) (2026)
- [Do You Trust Me? Cognitive-Affective Signatures of Trustworthiness in Large Language Models](https://mlsanity.com/paper/2601.10719/) (2025)
- [A BERTology View of LLM Orchestrations: Token- and Layer-Selective Probes for Efficient Single-Pass Classification](https://mlsanity.com/paper/2601.13288/) (2026)
- [RUVA: Personalized Transparent On-Device Graph Reasoning](https://mlsanity.com/paper/2602.15553/) (2026)
- [Are Emotion and Rhetoric Neurons in LLM? Neuron Recognition and Adaptive Masking for Emotion-Rhetoric Prediction Steering](https://mlsanity.com/paper/2604.17255/) (2026)
- [Some Emotions Run Deeper: Layer-wise Probing and Causal Intervention in Large Language Models](https://mlsanity.com/paper/2609.01279/) (2026)
- [Interpretable Symptom Vectors for Depression in a Large Language Model](https://mlsanity.com/paper/2609.01832/) (2026)
- [Usage-Modulated Sentiment Representations in Large Language Models](https://mlsanity.com/paper/2610.05069/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have rapidly become central to NLP, demonstrating their ability to adapt to various tasks through prompting techniques, including sentiment analysis. However, we still have a limited understanding of how these models capture sentiment-related information. This study probes the hidden layers of Llama models to pinpoint where sentiment features are most represented and to assess how this affects sentiment analysis. Using probe classifiers, we analyze sentiment encoding across layers and scales, identifying the layers and pooling methods that best capture sentiment signals. Our results show that sentiment information is most concentrated in mid-layers for binary polarity tasks, with detection accuracy increasing up to 14% over prompting techniques. Additionally, we find that in decoder-only models, the last token is not consistently the most informative for sentiment encoding. Finally, this approach enables sentiment tasks to be performed with memory requirements reduced by an average of 57%. These insights contribute to a broader understanding of sentiment in LLMs, suggesting layer-specific probing as an effective approach for sentiment tasks beyond prompting, with potential to enhance model utility and reduce memory requirements.