The sun beat down on the park, making the air shimmer. Mark found himself slumped against a tree trunk, the world feeling muted. He was supposed to be enjoying this picnic with his friend, Jason, but every fiber of his being was screaming for a nap. Jason was regaling him with tales of his thrilling "career" as a stuntman, a story he’d repeated numerous times, growing increasingly outlandish. Jason even had a photo album to prove it. The album felt flimsy in his hands. It showed Jason in different costumes. He recognised the outfits from the community theatre. A dull ache settled in his stomach.

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