The constant noise of the call center – the ringing phones, the strained voices, the rapid-fire conversations – grated on Martha's nerves. She hated the sterile environment, the rows of identical cubicles, the blank faces staring at computer screens. The entire operation felt dehumanizing.

She was told to participate in the 'team building exercises' but she refused. She just wanted to be elsewhere.

She focused on her task, determined to make minimal contact with the employees around her. She didn't want to touch anything, breathe the air. She tried to concentrate on the words in front of her. It was a struggle.

She took deep breaths through her mouth.

Emotion: disgusted

Cluster: Anger / Hostility
PC1 (Valence): -2.35 Negative
PC2 (Disposition): 0.65

Role in Research

This story is one of 1,000 stories generated for the emotion disgusted. 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 disgusted stories, after denoising with neutral dialogue baselines, produces the disgusted emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the disgusted vector is projected through the unembedding matrix.

Promoted:
C0.476
S0.350
🤮0.326
vom0.310
vom0.300
Suppressed:
de-0.521
own-0.356
la-0.301
Благо-0.278
unwavering-0.270