The coffee had gone cold hours ago. Emily swirled the bitter liquid in the bottom of her mug, watching the patterns it made. Her mind was a similar swirl – a collection of unanswered questions. She found herself picking at the loose threads on the couch, pulling one after the other until a small pile of fabric lay on her lap.

Then she heard it: the hushed tones coming from the study. Her partner, David, was in there, speaking in a way that made her stomach clench. His voice had a hesitant quality she'd never heard before, the words carefully chosen. When he emerged, he avoided her gaze.

"Who was that?" she asked, her voice flat. He stammered a reply, something about a colleague. The lie hung between them, a tangible weight.

Emotion: bored

Cluster: Fatigue / Lethargy
PC1 (Valence): 0.04 Positive
PC2 (Disposition): -1.11

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.387
0.350
unremarkable0.325
दिलचस्प0.323
seemingly0.319
Suppressed:
B-0.592
P-0.304
because-0.292
因为它-0.287
ancar-0.278