He’d had the audacity. Mark saw the notification flash across his laptop screen, and a surge of heat coursed through him, starting at his shoulders and radiating down his arms. His breath hitched. He spun around in his chair, a sudden movement that nearly sent his coffee mug flying.

He slammed his fist against the desk, the impact echoing through the quiet office. His eyes narrowed as he reread the name: *Brenda_Bane_Official*. He remembered the name; he remembered the relentless torment.

Mark began to furiously type, a scathing email drafted in his mind, ready to unleash the words he'd suppressed for years. He deleted it. He sighed heavily, the sound strained. He could feel the pulse in his temple throbbing.

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