"Amateur hour," the critic had sneered about Chef Maria's paella. Maria stared at the offending review, the words a bitter taste in her mouth. She found herself meticulously arranging and rearranging the spices on a shelf, a fruitless attempt to find some satisfaction. The restaurant, usually a bustling hub of activity, felt sluggish, and she felt the same. She felt as though she was stuck in place, as if her feet were trapped in wet cement. She had no energy to cook. She looked at her phone, and scrolled through the same social media posts she'd seen multiple times before.

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