The email sat in Leo’s inbox, glowing with the malevolence of a digital virus. He re-read the subject line: “Academic Integrity Inquiry.” His stomach dropped, a cold, heavy stone. He gripped the edge of his desk, knuckles white. His pulse hammered a frantic rhythm against his temples. He felt a bead of sweat trickle down his spine, despite the air conditioning. He swallowed hard, trying to dislodge the feeling of a lump in his throat.

He swiveled in his chair, staring out the window. The campus, usually a source of comfort, now seemed to mock him with its normalcy. Students strolled, laughing, oblivious to the turmoil churning inside him. He clicked the email open, bracing himself.

Emotion: uneasy

Cluster: Fear / Anxiety
PC1 (Valence): -1.80 Negative
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😰0.240
😖0.231
😣0.231
느껴0.226
worse0.222
Suppressed:
de-0.474
la-0.465
happy-0.261
a-0.255
ecstatic-0.228