He’d always hated weddings, a sentiment echoed in the tight knot forming in Daniel’s stomach. Especially this one. Sarah. God, it had been two years, but the sting was as fresh as a paper cut. He’d hoped, truly hoped, she wouldn’t be here. He scanned the room, each face a potential landmine.

Suddenly, there she was, chatting animatedly with the bride’s sister. He felt a wave of nausea, a dizzying sensation that threatened to pull him under. He squeezed his eyes shut for a moment, then forced them open. He felt like he'd been kicked in the chest.

His gaze flicked away, landing on the buffet table. He piled his plate high with indifferent food, barely tasting the bland offerings. He needed to avoid her. He needed to disappear.

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