He ran a hand through his hair, a gesture that usually soothed him. It did nothing now. His eyes scanned the article, a poorly-formatted mess, but the words were unmistakable. His clumsy poetry, his hopeless crushes, his fervent declarations of rebellion – all available for anyone with an internet connection.

He’d known, of course, that once the book went live, the internet would devour it. He'd even considered that some of the quotes would be excerpted. But seeing it, this entire catalog of youthful yearning, this public airing of his private failures, felt like a physical blow. A laugh, sharp and brittle, escaped his lips.

He considered sending an angry email, starting a legal battle. He dismissed both ideas immediately. It was too exhausting. Instead, he reached for the bottle of whiskey he kept hidden in his desk. He took a long, slow swallow, letting the burn fill his throat.

Emotion: disdainful

Cluster: Anger / Hostility
PC1 (Valence): -0.31 Negative
PC2 (Disposition): 1.79

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.419
l0.404
S0.387
T0.282
I0.257
Suppressed:
own-0.335
unexpectedly-0.285
Suddenly-0.246
previously-0.245
until-0.242