mlsanityData to 7 Oct 2026

A Comparative Study on Affective Cues in Text Embeddings Across Psychological Emotion Theories

arXiv 2606.29068 ↗First posted 27 Jun 2026cs.CL cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Text encoders are known for their utility in natural language processing, as they are able to efficiently compress inputs into dense vectors while preserving semantics. These models have been applied to affective computing, in particular to help with solving sentiment analysis and emotion recognition tasks. Nevertheless, it remains unclear to what extent the latent representations produced by modern text encoders capture well-defined psychological theories of affect. In this work, we investigate the affective capabilities of twelve recently released text encoders by probing their generated embeddings as input features for solving regression and classification tasks across three established emotion frameworks, using both word- and sentence-level data. Additionally, we apply a semantic data-leakage prevention technique to improve robustness in word-level evaluations. Our main findings show that the latent manifolds of the latest instruction-aware open-weight encoders enclose an equal or even a larger amount of affective information in comparison with proprietary counterparts when evaluated at word level. In contrast, embeddings of task-tuned and proprietary encoders reach the highest scores on sentence-level affective classification. Furthermore, a qualitative analysis of latent representations and their encoded affective cues is provided.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 59 references that are in the map. First posted on arXiv 27 Jun 2026.

Builds on

29 of 59 references.

References · 29

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  4. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  5. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  6. 2016Enriching Word Vectors with Subword Informationcited by 1,578
  7. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,175
  8. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,050
  9. 2022MTEB: Massive Text Embedding Benchmarkcited by 623
  10. 2020GoEmotions: A Dataset of Fine-Grained Emotionscited by 479
  11. 2021Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Modelscited by 462
  12. 2018From Louvain to Leiden: guaranteeing well-connected communitiescited by 379
17 more
  1. 2022One Embedder, Any Task: Instruction-Finetuned Text Embeddingscited by 329
  2. 2016Counter-fitting Word Vectors to Linguistic Constraintscited by 138
  3. 2025Gemini Embedding: Generalizable Embeddings from Geminicited by 93
  4. 2025jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrievalcited by 72
  5. 2023Emotional Intelligence of Large Language Modelscited by 58
  6. 2017Word Affect Intensitiescited by 51
  7. 2025Llama-Embed-Nemotron-8B: A Universal Text Embedding Model for Multilingual and Cross-Lingual Taskscited by 46
  8. 2025Training Sparse Mixture Of Experts Text Embedding Modelscited by 32
  9. 2025NRC VAD Lexicon v2: Norms for Valence, Arousal, and Dominance for over 55k English Termscited by 25
  10. 2019Dimensional Emotion Detection from Categorical Emotioncited by 24
  11. 2022Leveraging Label Correlations in a Multi-label Setting: A Case Study in Emotioncited by 14
  12. 2025Emotions Where Art Thou: Understanding and Characterizing the Emotional Latent Space of Large Language Modelscited by 14
  13. 2021Using Knowledge-Embedded Attention to Augment Pre-trained Language Models for Fine-Grained Emotion Recognitioncited by 10
  14. 2020Towards Label-Agnostic Emotion Embeddingscited by 9
  15. 2022Using Emotion Embeddings to Transfer Knowledge Between Emotions, Languages, and Annotation Formatscited by 7
  16. 2019Emotional Embeddings: Refining Word Embeddings to Capture Emotional Content of Wordscited by 4
  17. 2023Retrofitting Light-weight Language Models for Emotions using Supervised Contrastive Learningcited by 2

Built on by

Not cited yet.