Heavier than usual, the blanket felt like a lead weight as Michael stumbled out of bed. His limbs moved with the slowness of treacle. He had agreed to meet Alex for a game of pool, something he usually looked forward to, but today, the thought felt like climbing a mountain. Alex was always telling fantastical tales of his daring exploits as a "freelance journalist." Tonight, it was a story about an undercover investigation in a war zone. But the details were always hazy, the locations impossible. As Alex spoke, his eyes danced with a strange, almost feverish energy. Michael noticed Alex's phone vibrate. When he looked, Michael saw that it had an email open from the library staff. Michael felt a sudden chill, a knot forming in his chest.

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
à°­à°¿-0.214