The email sat in Eleanor’s inbox, unread. She could practically feel the cold prickle of the notification buzzing in her pocket. It was from the literary agent, the one who’d helped her get her own debut novel published. She’d always admired Jasper Thorne, the author whose work had inspired her. Now, she just wanted to crumple the screen.

She finally opened the email. The agent had included a link to an article, one that painstakingly detailed the similarities between Thorne's latest bestseller and Eleanor’s previously published short story. A wave of nausea rolled over her. She knew, even before clicking the link. She just knew.

Later, she’d find herself staring at the framed first edition of Thorne's signed book on her shelf. She picked it up, her fingers tracing the author’s bold signature. It felt like holding a snake. The edges of the paper cut into her palm. She tossed it onto the floor.

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