The university’s financial aid office was a blur of harsh lighting and hushed voices. Chloe waited, clutching the paperwork. It had been three weeks since the email, and the knot in her stomach had yet to loosen. Her palms were slick with sweat.

She watched the woman behind the counter, her face impassive. It was a mistake, a regrettable error. The scholarship was meant for someone else, the woman explained, her tone devoid of emotion. Chloe felt herself starting to tremble.

The room seemed to tilt slightly. She concentrated on steadying her breathing, focusing on the rhythmic in-and-out. She imagined herself back home, back in the quiet fields of her childhood, but the image wouldn’t hold. It flickered and dissolved into a swirl of uncertainty.

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