He wanted to scream. Michael sat rigid in the uncomfortable plastic chair of the community center, across from David. David, who’d boasted about being a renowned art dealer, the reason why Michael was so excited to tell him about his latest passion project. Now, the truth had come out: he was a janitor. A wave of nausea rolled through him. He found himself unable to make eye contact, focused solely on the cracks in the linoleum floor. The silence stretched, heavy and filled with unspoken accusations.

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