The email arrived on a Tuesday, subject line: “Scholarship Update.” Amelia, mid-lecture, barely registered the notification. Later, she’d been forced to read the words in the email aloud to a stern-faced administrator in a small, windowless office.

After, the afternoon sun felt harsh and unforgiving against her skin. She walked to the library, the familiar scent of old books failing to soothe her. As she navigated the stacks, she caught a glimpse of the offending email on her laptop screen. The words blurred, the cursor blinking, as if to deliberately taunt her.

She had to remind herself to breathe, her ribs tightening with each inhale. She didn't want to break the mouse, or throw the laptop, or scream. But she wanted to leave, right now.

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