The phone rang, and Leo answered it with a cheerful greeting, expecting his usual call from Mr. Silva, his acting coach. Instead, it was a curt message from the studio informing him that Mr. Silva had left the company. Leo dropped the phone, the plastic clattering on the floor.

His apartment suddenly felt too small, the walls closing in. The scripts he’d been diligently practicing, the acting exercises that filled the room with life, now felt like empty props. He ran a hand over his face, his skin prickling with sweat. The world felt muffled, distant. He needed to understand. He wanted answers.

He paced his apartment, muttering incoherent phrases, each word a desperate plea in the quiet emptiness of his home.

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