He stared at the email, his eyes struggling to focus in the dim light of the library. It was his college essay – the one he’d labored over for weeks. The essay about finding solace in books. Now, it was being used as an example, alongside other essays.

He remembered the late nights, the endless revisions, the feeling of pressure. He remembered the sense of excitement when the application was finally sent. Now, seeing it published, he felt a strong connection to his past self.

He picked up a well-worn copy of “Pride and Prejudice” from the shelf. He ran his fingers over the cover, the embossed title familiar to him. He opened it and slowly began to read, feeling a comforting sense of peace settle over him. He sank deeper into the pages.

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