The email arrived like a punch to the gut. Dr. Aris would be departing at the end of the semester. Amelia stared at the words, her breath catching in her throat. She re-read the sentence three times, as if the meaning might shift with each scan.

Her fingers tightened around the worn handle of her coffee mug. She hadn't finished her thesis yet. Panic, cold and clammy, spread across her skin. Now what? She'd spent two years under Aris’s guidance.

She glanced at her reflection in the darkened window of the coffee shop, smoothing down the stray hairs that had escaped her bun. A nervous habit. She felt a flush rising in her cheeks. The woman staring back looked like a fraud.

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