The laughter in the comedy club felt canned to Owen. "Olivia" was sharing stories, and each one echoed in his memory, a distorted version of a previous experience. The descriptions of her friends, the places she frequented, it was all too similar. The jokes felt flat. He shifted uncomfortably in his seat.

When she leaned closer, he instinctively recoiled. His pulse quickened. He mumbled something about needing air and got to his feet, walking to the exit. The neon lights of the city felt too bright and the sounds of the crowd, a deafening cacophony. He felt trapped.

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