She slammed the file onto her desk. The action, sharper than intended, echoed in the otherwise quiet office. Amelia’s heart hammered against her ribs, a frantic drumbeat. Her breath hitched. The conversation with HR, the one where she’d discovered the truth about David’s salary, kept replaying in her mind.

She picked at a loose thread on her sleeve. She'd always been a diligent worker, a team player, consistently exceeding expectations. David, on the other hand, was... well, David.

"Just breathe," she muttered to herself, her voice a near-whisper. The air felt thick, difficult to swallow. She leaned back in her chair, staring at the ceiling tiles, each one blurring slightly.

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