The weight of the day clung to Henry like a wet blanket. He felt sluggish, his movements slow, his thoughts muddled. He’d spent the afternoon staring out the window, watching the leaves fall, each descent a symbol of lost time. Now, he sat at the kitchen table, staring at a half-eaten bowl of cereal.

His gaze fell on the stack of notebooks on the counter, the ones belonging to his husband, John. John was always jotting things down, ideas for his stories. The top notebook was open. He knew he shouldn't. But his hand reached out and flipped it open. The first sentence was about him, about their morning ritual, about the precise way he took his coffee.

His breath hitched. He closed the book, then slowly opened it again, a fresh wave of something akin to betrayal washing over him.

Emotion: gloomy

Cluster: Sadness / Despair
PC1 (Valence): -1.68 Negative
PC2 (Disposition): -1.37

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.368
无法0.319
πŸ˜”0.300
い぀も0.270
μ“Έ0.255
Suppressed:
la-0.432
l-0.419
de-0.398
B-0.294
!-0.259