The email arrived late at night, a sterile subject line: "Departure Notice." David stared at the screen, his jaw clenched. His mentor, Ms. Chen, had been his rock, his guide through the cutthroat world of corporate finance. He reread the brief message, a cold formality that felt like a slap in the face. A void opened up inside him, an aching emptiness where her unwavering support had resided.

He slammed his laptop shut, the metallic clang echoing in his sterile apartment. He paced the small living room, his hands stuffed deep into his pockets. He felt a burning sensation behind his eyes, a prickling heat that threatened to spill over. He had so many questions, so much left unsaid. His stomach began to churn, and he fought back the urge to throw something.

He didn't sleep at all.

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