The city lights blurred through the rain-streaked window of the train. Sarah stared out, lost in thought. The job promotion was the talk of the office. She and Peter were both in the running.

She closed her eyes and saw their early days, the endless meetings and all the coffee breaks. She felt a surge of warmth at how they had grown as colleagues and as friends.

A profound sense of familiarity, laced with an unfamiliar sadness, settled over her. She knew that even if they never saw each other, they would always have that bond.

She clutched her handbag tightly. The thought of losing that shared experience, of the future changing, felt like a departure. She didn't want to let go.

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