He’d always been a show-off, even back then. Now, here he was, Dr. Michael Davies, PhD, sitting behind a large, mahogany desk, a picture of studious contemplation. Emily leaned back in the chair, arms crossed, the leather cold against her skin. The sunlight streamed through the window, highlighting dust motes dancing in the air, a stark contrast to the sterile perfection of the office.

“So, Emily,” Michael began, his voice smooth, professional, “tell me what brings you here today.”

She met his gaze, a carefully constructed mask of disinterest in place. “Just trying to fix something broken, I suppose.” She let the words hang, a subtle jab, a reminder of the games they'd played – the ones he'd always won. The ones that had chipped away at her self-esteem.

His gaze flickered, a tiny muscle in his jaw clenching for a fraction of a second. She enjoyed the brief flicker of discomfort.

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