mlsanityData to 7 Oct 2026

Probing Spectrum-Like Organization of States of Mind in Transformer Representation Spaces

arXiv 2512.22227 ↗First posted 23 Dec 2025cs.CL cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We investigate whether graded states of mind form spectrum-like structure in transformer representation spaces. To do so, we construct a dataset of 636 short natural-language sentences annotated with both a continuous score from -5 to 5 and one of seven ordered tiers, ranging from collapsed or scarcity-driven expressions to more coherent, reflective, and integrative ones. We evaluate five frozen transformer representations: four sentence-embedding models and one decoder-only residual-stream representation. Across all representations, simple probes reliably recover both the continuous score and the discrete tier labels, and permutation tests show that performance significantly exceeds shuffled-label baselines. Additional analyses reveal a consistent geometric pattern: UMAP projections show low-to-high organization, confusion matrices concentrate errors between neighboring tiers, and directional ablation identifies a prominent score-aligned component. These results suggest that transformer representations contain statistically significant, spectrum-like organization aligned with the annotated state-of-mind structure. The annotations are used only as an operational framework for representation analysis, not as a clinical or diagnostic measure.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 25 references that are in the map. First posted on arXiv 23 Dec 2025.

Builds on

19 of 25 references.

References · 19

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  4. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,414
  5. 2016Understanding intermediate layers using linear classifier probescited by 1,279
  6. 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 973
  7. 2019How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddingscited by 770
  8. 2023The Linear Representation Hypothesis and the Geometry of Large Language Modelscited by 679
  9. 2023The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasetscited by 673
  10. 2019Designing and Interpreting Probes with Control Taskscited by 608
  11. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 556
  12. 2020GoEmotions: A Dataset of Fine-Grained Emotionscited by 479
7 more
  1. 2018What you can cram into a single vector: Probing sentence embeddings for linguistic propertiescited by 452
  2. 2023Language Models Represent Space and Timecited by 306
  3. 2025Persona Vectors: Monitoring and Controlling Character Traits in Language Modelscited by 303
  4. 2018Analysis Methods in Neural Language Processing: A Surveycited by 276
  5. 2023Linear Representations of Sentiment in Large Language Modelscited by 157
  6. 2025Emotions Where Art Thou: Understanding and Characterizing the Emotional Latent Space of Large Language Modelscited by 14
  7. 2025Emergence of Hierarchical Emotion Organization in Large Language Modelscited by 6

Built on by

Not cited yet.