He had been enjoying a quiet afternoon, a rare luxury. Then, the Amazon notification. "Your book has been shipped." "The Reluctant Poet: The Story of Daniel Blackwood." He felt a cold dread sink into his bones. He knew nothing about it. His poetry was private. Sacred.

He reread the email, his eyes scanning for some sign of a mistake. There wasn't one. He felt a sudden, intense heat, a flush spreading from his neck to his face. He grabbed the phone and dialed a number, his knuckles white.

Daniel spoke into the phone, his voice tight, clipped. He did not care about politeness. He did not care about the consequences. He had to put a stop to this. He had to protect his words.

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