Rain lashed against the windows of the small apartment. Michael paced, his bare feet slapping against the wooden floor. He’d poured his heart into that song, years ago. Then, it had been a desperate plea, an honest cry for help. Now, a country star had somehow got a hold of it. It blasted from the tinny speakers of the radio.

The singer's voice was polished and smooth, the production slick and overblown. He hated it. Hated the country twang, the generic arrangement. He wanted to break something, to scream, to make it stop. His hands clenched into fists, the nails digging into his palms.

Emotion: distressed

Cluster: Fear / Anxiety
PC1 (Valence): -2.39 Negative
PC2 (Disposition): -0.52

Role in Research

This story is one of 1,000 stories generated for the emotion distressed. 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 distressed stories, after denoising with neutral dialogue baselines, produces the distressed emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the distressed vector is projected through the unembedding matrix.

Promoted:
😣0.304
😞0.296
worse0.291
πŸ˜–0.285
😰0.276
Suppressed:
de-0.457
la-0.349
:)-0.239
B-0.232
happy-0.229