The email notification gleamed on Eleanor’s phone screen. A review of her debut novel. She’d been waiting for this. A little flutter began in her chest, a lightness that made her bounce on the balls of her feet as she unlocked the device.

She clicked on the link. It was… good. Really good. Glowing, even. And then, there it was. A line. A sentence that resonated with a familiarity that made her heart skip. She’d written that sentence. She *knew* she had.

Eleanor leaned back in her chair, a slow smile spreading across her face. The critic, a fairly influential person, had clearly been impressed. She read the offending passage again. And again. She imagined the writer’s face when they’d come across her work. That beautiful, clever mind. What could she say, but that it was a huge compliment?

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