The spreadsheet blurred before Amelia's eyes. Another quarterly report, another mountain of data she already knew by heart. She drummed her fingers against the cool metal of her desk, a restless rhythm that echoed the thrumming in her temples. The air conditioning hummed, a monotonous drone that seemed to amplify the silence. She glanced at the clock; it ticked forward at agonizing slowness.

Across the open-plan office, Kevin, her coworker, was whistling, oblivious to the tedium. He caught her eye and gave her a cheery wave. Amelia forced a smile back, her lips feeling stiff. She swiveled in her chair, seeking a different angle, anything to break the monotony.

“Hey, Amelia,” Kevin called. “Ever been to Camp Clearwater?”

Amelia’s jaw dropped. Clearwater? Her throat felt tight. “Yeah… I mean, I went there when I was a kid. Why?”

Kevin’s grin widened. “No way! So did I! Cabin 7, year I graduated high school.” He leaned forward, eyes sparkling with sudden animation. "Remember the talent show? I played the kazoo so badly…”

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