The world felt gray to Eleanor. Even the normally boisterous chatter of the café seemed to fade into a dull hum. She sat at a table by the window, swirling the lukewarm coffee in her cup, the bitterness mirroring the taste in her mouth. She had asked her partner, David, to pick up some groceries, so she waited.

She idly picked up David's laptop, left open on the table. Curiosity, a rare spark in her current state, flickered. She’d always known he was a writer. Now, she understood why he was always staring at her. The document on the screen was a novel. And the main character had her name, her quirks, her habits.

Her hands started to shake. The coffee sloshed over the rim of the cup.

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
😔0.300
いつも0.270
0.255
Suppressed:
la-0.432
l-0.419
de-0.398
B-0.294
!-0.259