He glared at the email notification on his phone. Plagiarism. The audacity. He’d spent weeks on this project, sacrificing his weekends, fueled by instant coffee and a burning ambition to prove himself. Now this? He slammed his phone down on the desk, the cheap plastic rattling against the chipped surface.

He'd known, of course. He'd seen the way Professor Chen had looked at him in the hallway that morning. The condescending little smirk that seemed to say, "I knew you wouldn't be able to handle it." He clenched his fists, knuckles turning white.

“This is ridiculous,” he muttered, more to himself than to the empty room. He pictured Chen’s office, the carefully curated bookshelves, the air of self-importance. He was tempted to march right over there and… well, he wasn't sure what he wanted to do, but it wouldn't be pleasant.

The tightness in his chest intensified. He had a reputation to uphold. A legacy, even. And this… this was an insult. A blatant, undeserved slight on his character. He took a deep, ragged breath and opened the document again, his jaw set.

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