The weight of the information settled on Ben's shoulders like a physical burden. He'd seen the numbers. The junior data analyst was compensated far beyond his own salary. He ran a hand through his hair, the gesture almost frantic.

He stared at his computer screen, the bright light reflecting in his eyes, feeling trapped. He needed to get out of the office. He grabbed his jacket, mumbling something about a quick errand. He had to escape, even for a few minutes.

He found himself walking aimlessly, with no destination in mind, the injustice a bitter taste on his tongue.

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