The coffee cup trembled in Amelia's hand, sloshing dark liquid onto the pristine white tablecloth. Mark, her supposed "financial advisor," the man she’d trusted with her life savings, had confessed. He wasn’t advising anyone. He was a glorified telemarketer. Her knuckles were white as she gripped the porcelain, feeling a coldness seep from her chest to her fingertips. The cafe, usually a comforting space, suddenly felt suffocating, filled with judging eyes and whispers that she imagined. She stood abruptly, knocking over her chair, and fled the establishment.

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