“Well, this is unexpected,” Michael muttered, staring at the screen. The listing for his childhood home had popped up while he was idly browsing. The reality of it, the cold concrete of the listing and all its slick imagery, hit him with a physical force.

He tried to focus, to read the details, but his vision blurred. He felt sluggish, unable to engage with the words. His shoulders slumped, and he stared blankly, the vibrant photos becoming a jumble of colors, a world away from his memory. He felt the impulse to just shut the whole thing down, switch off the computer, and crawl into bed.

Emotion: tired

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.92 Negative
PC2 (Disposition): -1.00

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
weary0.254
fatigue0.249
😴0.238
sighed0.237
barely0.230
Suppressed:
C-0.268
because-0.225
B-0.219
🤟-0.217
భి-0.214