The email arrived, another missive from Daniel, detailing his "strategic leadership" at some non-existent tech firm. His signature, always so carefully crafted, seemed to mock her. She knew, she *knew*, Daniel was unemployed. She’d seen him, more than once, lurking around the local library, pretending to read business journals.

She deleted the email without reading it. The whole thing was just exhausting. She pictured him, hunched over his computer, composing these elaborate fictions, and a cold wave passed through her.

She glanced at the photo on her desk, a picture of them both laughing, taken years ago. The memory of their shared history felt tainted, polluted by the current dishonesty. She spun her chair away from her desk, needing to escape the suffocating weight of it all.

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