He had revered Jasper Thorne. For years, Leo had meticulously collected every first edition, annotated every interview, devoured every word. Now, the man was a fraud. Leo crumpled the offending article in his hand, a frustrated sound escaping his lips. He hadn't slept since he read the news.

He walked over to the bookshelf, running a hand along the spines of Thorne's novels. The vibrant covers mocked him. He yanked one book out, tossing it onto the floor, the sound of the pages hitting the hardwood a gunshot in the silent room.

His phone buzzed, a notification from a friend who’d excitedly texted him about the scandal. The thought of feigning enthusiasm – as he’d done so many times with his literary hero – made him gag. He turned his phone off, unable to face the world and the way it would view Thorne, and by extension, him, too. He sat down and stared at the mess he'd made.

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