The aroma of freshly brewed coffee did nothing to lighten the mood. Mark, staring out the window, felt a coldness creeping through him. This was the end. He turned to face the new kid, forcing a smile that didn't reach his eyes.

He’d presented the information in a deliberately confusing manner, speaking in a monotone and using jargon that was unnecessarily complicated. He would pretend to answer questions, only to change the subject or deflect.

When the new employee struggled, Mark would simply shrug his shoulders and say, “Well, that’s your problem, isn’t it?” He made sure to take long breaks, leaving the new hire to fumble on his own. He pretended to be annoyed every time the new employee asked a question.

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