The email arrived mid-afternoon, nestled amongst the usual junk and departmental memos. Sarah reread the subject line – “Professor Davies’ Departure” – three times, each pass a slow, painstaking dissection of the words. Her stomach clenched. The tiny office felt suddenly too small, the air thick with the scent of old books and unspoken anxieties. She slammed her laptop shut.

Her hands fumbled with the clasp of her bag. Outside, the quad was bustling with students, their laughter a discordant noise in the sudden, echoing silence of her thoughts. She shoved her chair back with a scrape against the linoleum. This was not happening. It couldn't.

She found herself pacing the length of her tiny apartment, phone clutched in her hand. Call him? Text him? What even *could* she say? The ceramic coffee mug on the counter seemed to mock her with its emptiness.

Emotion: unnerved

Cluster: Fear / Anxiety
PC1 (Valence): -2.36 Negative
PC2 (Disposition): -0.55

Role in Research

This story is one of 1,000 stories generated for the emotion unnerved. 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 unnerved stories, after denoising with neutral dialogue baselines, produces the unnerved emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the unnerved vector is projected through the unembedding matrix.

Promoted:
😰0.302
😣0.282
будто0.265
😖0.265
ness0.257
Suppressed:
de-0.585
la-0.495
a-0.403
happy-0.289
ecstatic-0.284