The cafe was filled with the gentle clatter of cups and the murmur of conversations, but Maya felt isolated, adrift in a sea of white noise. She stared blankly at the cappuccino in front of her, the foam already beginning to dissipate. The day held no promise of entertainment.

She clutched a dog-eared paperback of "The Crimson City," by the celebrated author, Isla Thorne. Maya had been mesmerized by Thorne's evocative descriptions and intricate plots. She'd wanted to be a writer too, someday.

A recent online article, passed along by a disgruntled friend, had suggested that the author was less than honest. Maya had scoffed, but she couldn’t shake the feeling. She pulled out her phone and started searching. Her heart sank.

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