He nearly tripped over the package as he left for work. The damn thing was huge, addressed to “Ms. Eleanor Abernathy, Apt. 3B”. He’d never even met an Eleanor Abernathy. The previous tenant, a woman who’d left behind a collection of dead plants and a faint odor of stale perfume. He nudged it with his foot, the cardboard yielding slightly.

As he walked down the street, he imagined the contents: probably some overpriced cat food or a self-help book about finding inner peace. He chuckled grimly. Inner peace. He’d be lucky to find a parking space.

He'd leave it on the front steps, where the rain could get to it. Maybe the elements would provide the catharsis he so desperately craved. It would save him the inconvenience of dealing with it.

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