John felt his jaw clench so tight he thought his teeth might crack. He'd just seen a social media post, a picture of David, his supposed "venture capitalist" buddy, flipping burgers at a charity event. The same David who’d "invested" in John’s failed app idea, then brushed him off with vague promises of future opportunities.

A wave of heat flooded his face. He’d spent countless evenings listening to David’s supposed business acumen, his tales of mergers and acquisitions, all the while silently judging his own lack of success. Now, the roles were reversed, and John found himself utterly bewildered and mortified.

He wanted to scream. Instead, he slammed his laptop shut, the metallic clang echoing in the otherwise silent apartment. The screen displayed the words, “David Miller - CEO.”

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