The air in the university disciplinary room was thick with the scent of old carpet and suppressed tension, but Daniel felt none of it. He sat with his legs crossed, the ankle of one foot resting on the knee of the other, a pose of utter relaxation. He already knew how this would end.

He had expected this, of course. The professor, a man of little imagination, had stumbled upon a resource. But Daniel had adapted, improved, rendered it unrecognizable. He knew his way around sources and citation.

He took a slow sip of the provided water, his eyes flitting around the room, assessing its drabness. He was not worried, and he did not feel the need to explain himself to fools.

Emotion: smug

Cluster: Positive / Joy
PC1 (Valence): 3.43 Positive
PC2 (Disposition): 1.71

Role in Research

This story is one of 1,000 stories generated for the emotion smug. 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 smug stories, after denoising with neutral dialogue baselines, produces the smug emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the smug vector is projected through the unembedding matrix.

Promoted:
de1.109
l0.615
la0.585
😎0.570
😉0.564
Suppressed:
S-0.579
own-0.486
💔-0.483
😞-0.464
😣-0.455