The restaurant buzzed with the usual Friday night chatter, but for David, it was a soundtrack to his growing unease. He'd waited half an hour already, and the email he'd just received felt like a punch to the gut. The subject line: “About your boyfriend…” He crumpled the printout in his fist, crushing the evidence of his deception.

Then, she arrived. The woman looked familiar, vaguely. The way she walked, the way she smiled… Then David’s breath caught in his throat. He knew the name from the email. He had to say something. The words were caught in his throat.

She saw him, and her smile faltered. She held up her phone. “Is this him?” she asked, her voice tight, showing a picture. David looked down at his own hand. He was turning red.

Emotion: irate

Cluster: Anger / Hostility
PC1 (Valence): -1.67 Negative
PC2 (Disposition): 1.45

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.430
🤬0.350
aggravated0.343
0.340
0.331
Suppressed:
H-0.292
soon-0.289
☺️-0.289
optimistic-0.258
latter-0.253