The email arrived like a sudden blow. “Featured Essay of the Week!” He’d spent hours, days, crafting those words, pouring his anxieties and hopes onto the page. Now, they were on display, public property. The blood drained from Michael's face.

He reread the email, each word a fresh stab. He felt a tremor in his hands as he dropped his phone. He kicked a chair, the wood connecting with a loud thud, and then regretted it immediately. He picked up the phone, still trembling, and slumped onto the couch.

He stared at the ceiling, unseeing, feeling a rising sense of claustrophobia. The world around him seemed to shrink, closing in. He needed air, space, to think. He grabbed his jacket, his movements jerky, and fled outside.

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