The spreadsheet shimmered, mocking him. Mark, a Senior Analyst with five years under his belt, stared at the numbers. Sarah, barely a year out of university, was earning more. He ran a hand through his hair, the gesture rougher than usual. His jaw clenched.

He excused himself from the team lunch, muttering something about a "prior commitment." The fluorescent lights of the office hallway seemed to hum, a discordant tune against his frustration. He needed air.

Outside, he sat on the curb, the sun hot on his face, though he barely registered it. He could feel a knot twisting in his gut, and his hands were clammy. This wasn’t fair. He’d put in the time, the effort, the extra hours.

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