The doctor’s office felt too bright, the fluorescent lights humming a sickly tune. Clara clutched the offending document, a glossy printout that revealed a diagnosis she most certainly *didn't* have: Stage II melanoma. She fixed her gaze on the well-meaning doctor, whose attempts at explanation seemed to bounce off her like rubber balls. He kept repeating "mistake," "similar names," "regrettable error." She merely tapped her manicured fingernails against the table. The tapping grew faster, a frantic rhythm against the sterile silence.

“So, you’re saying… I’m fine?” she finally asked, her voice tight, a thin wire stretched to its breaking point. The doctor nodded eagerly, relief flooding his face.

She stood abruptly, the chair scraping against the floor. “Right,” she said, her smile brittle, a display for public consumption. "Well, I suppose that’s just *wonderful*.” She didn't offer a handshake, didn't bother with a goodbye. She just walked out, the crisp document clutched in her hand like a weapon, the sunlight outside seeming suddenly harsh.

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