The waiting room seemed to shrink, the chairs closing in on him. John tapped his foot impatiently, a rapid staccato against the linoleum floor. The accusations had created a burning in his chest. His palms were slick with sweat. He felt trapped.

He kept replaying the professor's words in his head, searching for a glimmer of understanding, an admission of error. He found none. He felt his jaw tighten, his muscles clench. He wanted to break something, anything. He couldn't wait to get out of there.

Emotion: irritated

Cluster: Anger / Hostility
PC1 (Valence): -0.86 Negative
PC2 (Disposition): 1.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.370
S0.282
P0.264
😠0.248
aggravated0.233
Suppressed:
own-0.300
joyful-0.211
joyous-0.207
खोले-0.206
newfound-0.205