The news arrived as Leo was meticulously formatting his bibliography. Professor Bell was departing. He let out a low whistle of surprise, then a soft chuckle. He leaned back in his chair, stretching his arms above his head. He hadn't expected this.

Bell's constant nitpicking and passive-aggressive suggestions had been an ongoing irritation. Leo had been careful, meticulously so. Now, though, the constant nagging was over. He ran through the chapters, seeing them in his mind. He was confident of the strength of his work.

He closed his laptop, a satisfied sigh escaping his lips. He'd always known he had a good thesis. Now, it was just a matter of showing it to someone who would *get* it. He felt the tension he didn't know he was holding, melt away. He’d begin the search immediately for a new, supportive advisor.

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
πŸ˜‰0.564
Suppressed:
S-0.579
own-0.486
πŸ’”-0.483
😞-0.464
😣-0.455