The notification pinged. Another follower. Another retweet. Chloe tapped a manicured nail against her phone screen, a small smile playing around her lips. The online version of *Tears & Tiaras: My Awkward Years*, her teenage diary, had been live for all of twenty-four hours, and already the comments were flooding in. A particularly witty one about her pre-braces smile brought a genuine chuckle. She’d always known she was destined for internet stardom, and now, finally, the world would see it.

Chloe stretched languidly in her plush velvet armchair, a vision of effortless chic in her silk robe. She took a sip of her Earl Grey, the steam momentarily clouding her face. It was all so predictable, really. The predictable success, that is. She’d always been a cut above the rest, and now the rest were finally catching up.

Her phone buzzed again, this time a direct message. "OMG, you were SO dramatic back then!" it read. Chloe chuckled, the sound like wind chimes. She composed a witty reply, one perfectly calibrated to leave her admirer hanging on her every word. This was just the beginning.

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