The fluorescent lights of the break room hummed, a sound that grated on Amelia's nerves like fingernails on a chalkboard. She stared at the half-eaten bagel on the table, barely resisting the urge to hurl it across the room. The email, with its cheerful subject line ("Exciting News!") had landed in her inbox a mere fifteen minutes ago, and her stomach had knotted since. Sold. The word echoed in her head, a cold, flat pronouncement.

She crumpled the email and tossed it into the overflowing trash bin, narrowly missing the rim. A sigh escaped her lips, a sound of profound boredom. The coffee tasted weak, as always. She poured it down the drain and went back to her desk.

The office air, thick with the scent of stale coffee and forced optimism, felt heavier than usual. She barely acknowledged her coworker's chirpy greetings.

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