The printer in Lisa's office whirred to life, spitting out a copy of the acquisition announcement. She watched it, her expression hardening. It was as if someone had just yanked the rug out from under her. Her meticulously organized desk seemed to mock her, the neatly stacked files suddenly representing wasted effort.

She found herself clenching her jaw, her shoulders stiffening. She felt a burning sensation behind her eyes. She wanted to yell, to scream. But she forced herself to breathe, forcing herself to look calm, even though everything inside was swirling.

“Well,” she sighed, a small brittle sound, “that's just great.” She leaned back in her chair, the leather squeaking in protest, and stared at the ceiling, feeling a profound sense of… loss.

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