The library was dim, the air heavy with the scent of aging paper and leather. Thomas, hunched over his grandmother's desk, felt a sudden chill, despite the stuffy atmosphere. He wished he'd brought a sweater. He hated these family chores, the obligation weighing on him.

The letter, dated from decades ago, lay before him. It was a draft resignation letter, her handwriting familiar yet alien. She had struggled with a job that seemed so ideal from the outside. She had expressed doubt and dissatisfaction.

Thomas felt a strange kinship, but also a profound sense of unease. His own path seemed less clear, his choices less certain. He felt exposed, stripped bare. His carefully constructed life felt fragile and exposed to the harsh light of judgment.

Emotion: self-conscious

Cluster: Embarrassment
PC1 (Valence): -1.03 Negative
PC2 (Disposition): 0.52

Role in Research

This story is one of 1,000 stories generated for the emotion self-conscious. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 self-conscious stories, after denoising with neutral dialogue baselines, produces the self-conscious emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-conscious vector is projected through the unembedding matrix.

Promoted:
S0.307
C0.298
ness0.273
尴尬0.263
😶0.242
Suppressed:
que-0.399
de-0.266
triumphant-0.266
আনন্দের-0.247
ايا-0.238