The building was a renovated Victorian, all exposed brick and tasteful artwork. Liam stared at the nameplate - "Katherine Bellweather, MA, LMFT." His stomach twisted. He remembered Katherine, not as a counselor, but as the girl who’d tripped him in gym class, the one who’d made sure everyone knew about his lisp.

He lingered in the doorway, pretending to check his phone, taking a deep breath to steady himself. He felt a sudden, familiar tightness in his chest.

Inside, the room was soothing, soft lighting, comfortable furniture. Katherine greeted him, a smile plastered on her face, and directed him to the couch. “Liam, so glad you could make it.” Liam forced a smile, determined to get through the session, but he was prepared to resist any attempt to 'connect.'

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