The steak tasted like shoe leather. David had picked the restaurant. He was treating. With his new, inflated salary. Robert, across the table, was smiling, offering congratulations. The smile felt like a mask. Robert had been training David for months, sharing his skills, his knowledge.

He took a long drink of water, the ice clinking against the glass. He could feel the heat rising in his face. His knuckles were white as he gripped his fork.

He looked around the restaurant, the happy families, the couples, the atmosphere of celebration, all seemed too bright, too loud.

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