He found the notification while scrolling through social media. A friend had shared the link: "Brilliant new piece by the esteemed Professor Eleanor Vance!" Daniel’s jaw clenched. It was his piece. He’d sweated over every word, every paragraph, every single excruciating detail.

He threw his phone onto the couch, the screen flashing an accusatory glare. The knot in his shoulders wouldn't release. He felt a throbbing pulse in his temples. How could they? After all the promises, all the assurances.

He drove to the university, ignoring the speed limit. The campus, usually a haven of knowledge and creativity, now felt like a cage. He pictured Vance, smugly presenting his work. He couldn't even bring himself to offer a polite nod in the hallways.

Emotion: scornful

Cluster: Anger / Hostility
PC1 (Valence): -0.76 Negative
PC2 (Disposition): 2.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.406
C0.391
S0.276
I0.268
0.243
Suppressed:
own-0.396
unexpectedly-0.288
Suddenly-0.260
soon-0.256
serendip-0.256