Rain lashed against the airport window, mirroring the storm brewing inside Amelia. She chewed on her lip, the taste of stale lipstick a bitter reminder of the presentation she was about to miss. Three days of preparation, countless late nights, and for what? To be stuck in this echoing terminal, surrounded by crying babies and stressed-out business travelers. Her stomach churned. The airline's automated voice droned on about unforeseen circumstances, but all Amelia heard was the death knell of her ambitions. She clenched her fists, nails digging into her palms, a frantic attempt to ground herself.

Emotion: upset

Cluster: Fear / Anxiety
PC1 (Valence): -2.30 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.395
😞0.303
无法0.246
ness0.238
unable0.238
Suppressed:
de-0.533
la-0.457
l-0.223
😎-0.215
🤩-0.210