β€œThis is a mistake,” John muttered, a low growl of frustration. He ran a hand through his hair, the gesture almost violent. The "D-" on his economics midterm felt like a personal affront. He'd poured over the textbooks for hours, sacrificed sleep, and this was the result? He felt a surge of adrenaline, a sudden urge to argue, to demand a regrade, to somehow rectify the injustice. He balled his fists, the knuckles white.

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