The email notification pinged, the digital sound a tiny needle prick. He clicked on it, the subject line a brutal punch to the gut: “Manuscript Decision.” He read the polite, pre-written words, a symphony of insincerity. He deleted the email immediately.

He went to the kitchen and grabbed a beer from the fridge, the cold metal a small comfort against his trembling hand. He opened the bottle with a loud *crack*. He sat at the kitchen table, staring out the window at the rain-streaked street. The world outside, always so bright, suddenly felt dull and unappealing.

He found himself scrolling through social media, a curated parade of successes, each post a fresh jab. He slammed his laptop shut, the sudden noise a release of pent-up anger.

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