The aroma of freshly brewed coffee did nothing to soothe the tension knotting in Clara’s shoulders. Mark was cheerfully pouring kibble into a bowl for the cat he’d insisted on adopting. The cat, a sleek Siamese, watched Clara with cold, amber eyes.

Clara busied herself with making toast, her movements sharp, almost jerky. The cat, having finished his meal, began pacing the length of the kitchen counter. The click of his claws on the countertop set her teeth on edge.

She avoided looking at Mark, at the cat, at the new litter box in the corner. She couldn’t explain the pressure in her chest, the feeling of something closing in. She just knew that she desperately wished they could go back to the way things were.

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