“And then, I was diagnosed with a rare tropical disease…” The woman’s voice, honeyed and false, poured over the microphone. Evelyn, sitting in the back of the auditorium, felt a coldness creep through her. The “biography” tour. She had to be here, for appearances.

Each manufactured detail, each cloying sentiment, felt like a physical blow. The author had interviewed her sister, her colleagues, even her dentist, weaving a tapestry of distorted truths.

Evelyn gripped the armrests of her chair, her knuckles turning white. Her chest felt constricted. The author continued, describing Evelyn’s supposed bravery. Evelyn wanted to interrupt, to scream the truth, to reveal the raw, unvarnished reality. Instead, she sat, stone-faced, and endured. The thought of confronting that woman was repellant.

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