He’d offered to pick up the tab at the pub, of course. “It’s the least I can do,” Robert had said, flashing a charming grin. Then he’d launched into another detailed account of his “consulting” business. John, on the other hand, knew Robert was unemployed and living off of his savings.

John stared at the foamy head of his beer. The words Robert were saying seemed to echo around him, creating a dull thrum inside his head. He gripped the glass, feeling the cool condensation against his skin.

He felt the muscles in his jaw clench, and shifted in the booth. His shoulders felt tight. He wanted to be anywhere else.

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