The aroma of instant ramen clung to the air, a familiar scent that usually comforted Ethan. Tonight, it made his stomach churn. He dropped his books on the desk with a clang.

His roommate, Sam, was staring intently at his phone, his brow furrowed in concentration.

"Dude," Sam said without looking up. "You look beat."

Ethan just shrugged, a slow, deliberate movement. The simplest tasks felt monumentally difficult. He wanted to do nothing, be nothing.

His limbs felt heavy, his mind sluggish. The thought of getting ready for bed felt like climbing a mountain.

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