The air in the diner felt thick, charged with a strange tension. Sarah kept picking at her nails, the rhythmic scraping a nervous counterpoint to the bittersweet conversation. When Maria announced she was moving to New York, the sudden jolt made Sarah feel like she'd been physically struck. She felt suddenly aware of every little thing about herself, every perceived flaw amplified by the bright diner lights.

She forced a smile, but it felt crooked and unnatural. She kept glancing at Maria, studying her face, searching for clues, for hints of the goodbye that was already unfolding. She felt a familiar knot of discomfort forming in her stomach.

She found herself fidgeting, shifting her weight from foot to foot. She played with the straw in her milkshake, bending it this way and that. She listened to Maria’s plans, her voice sounding small and insignificant. She felt exposed.

"New York will be great," she managed, her voice barely audible.

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