The email scrolled before him, each damning sentence a fresh stab. His shoulders slumped, and he felt a profound weariness settle over him, as if he'd run a marathon. The accusation, so casually delivered, had knocked the wind out of him. The words, "plagiarism detected," now glowed menacingly.

He closed his laptop, the screen reflecting his own stricken face. He found himself wandering aimlessly through his apartment, unable to concentrate, unable to find comfort in his usual routines. The injustice was like a constant ache. He ran a hand over his face.

The thought of his parents' disappointment was a fresh wave of despair.

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