Eliza paced the terminal, the polished floor reflecting her increasingly agitated form. Each time she passed a window, the setting sun seemed to mock her. The wedding was scheduled to begin in less than two hours, a fact that tightened her chest with every passing second. Her best friend, Sarah, was waiting.

She felt a furious heat bloom in her cheeks, and her jaw clenched until her teeth ached. She'd spent months planning the perfect speech, the perfect toast, meticulously organizing every detail of Sarah's bridal shower. And now? Now, she was stuck in this purgatorial airport, watching her carefully crafted plans unravel before her eyes.

A small, frustrated sound escaped her lips. She began to rapidly thumb through the airline's app, searching for any glimmer of hope. The estimated arrival time remained stubbornly unchanged. She imagined Sarah, smiling, awaiting her arrival. This thought only added fuel to her mounting fury.

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