The fluorescent lights of the cafe hummed, a monotonous drone that did nothing to soothe the tremor in Mark's hands. He kept running a finger around the rim of his coffee cup, the ceramic feeling cold and slick. He'd been friends with David since kindergarten, and now they were both vying for the same software engineering position.

David was across the table, explaining his latest coding project with animated gestures and a booming laugh. Mark, however, found himself staring at the intricate patterns of condensation on his glass, unable to focus on a single word. His palms were slick with sweat.

“So, what do you think?” David asked, his brow furrowed in concern. Mark stammered an answer, a jumble of half-formed sentences. He excused himself to go to the bathroom. He felt a need to be alone for a minute, the solitude offering an illusion of control.

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