The old jukebox in the diner crackled to life, and then… there it was. His song. But the singer… oh, the singer.

Michael felt a rush of heat to his face. He'd poured his heart into that song. He'd made a career of playing it in dark bars for barely enough money to eat. Now, a country singer with a booming voice was belting it out, complete with pedal steel and a cheesy video.

He slammed his fist on the table, rattling the salt shaker. He wanted to scream. He wanted to break something. He abruptly stood, leaving his half-eaten burger and a generous tip on the table.

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