The presentation was going swimmingly. Sarah could practically taste the accolades, the promotion, the envious glances from her colleagues. Her PowerPoint slides, a masterpiece of concise brilliance, were gliding across the screen. She barely glanced at the faces in the room. They weren’t worthy of her attention.

Her phone buzzed. She ignored it. This was her moment. A carefully constructed spreadsheet, which would change the company forever, had taken months, and the results were stunning. Now, she just had to walk through the logic with her presentation.

Then, David raised his hand. “Actually, Sarah, I think I have a similar project to share. It's on a comparable topic, and the final results… well, you'll see.” He had the audacity to grin. Sarah's jaw clenched. She tapped the pen on the table, trying to look unimpressed.

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