He found himself staring at the spreadsheet, the numbers blurring before his eyes. The conversation with Claire, her recollection of Camp Silverwood, echoed in his mind, and the walls of his office seemed to shrink. He ran a hand through his hair, a gesture he repeated frequently in times of stress.

He felt his breath quicken. He needed to go outside, to get air. The air conditioning suddenly felt stifling. He’d gone to great lengths to bury those summers, that place, those faces. Now, it had risen, like a specter, and it was walking toward him.

He pushed his chair back, the squeak of the wheels too loud in the sudden silence. His palms were slick with sweat. He rose, mumbling something about a quick walk to grab a snack.

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