The air was thick with the aroma of cinnamon and stale coffee. Leo, hunched over his laptop, scrolled through the manuscript he’d just discovered. His partner, Mateo, had been working on a novel for months, but he’d kept it secret. He'd never expected this.

He saw himself in the protagonist. The book was a love letter to their life, their shared adventures, their quiet nights in. Mateo had woven their daily interactions, their intimate moments, into an epic romance. He recognized the specific details, the familiar rhythm of their lives, captured in words.

He found himself smiling, a genuine, unguarded expression. A soft pressure built behind his eyes, a feeling he wasn't quite sure how to interpret. He imagined Mateo's face when he read it and the joy they might share.

Emotion: sentimental

Cluster: Nostalgia / Reflection
PC1 (Valence): 0.89 Positive
PC2 (Disposition): -1.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
L0.677
fondly0.567
memories0.503
0.488
reminis0.466
Suppressed:
either-0.515
or-0.488
[]-0.473
--0.408
не-0.396