The train rumbled along, each jolt sending a fresh wave of weariness through Emily’s limbs. Even the rhythmic clatter of the tracks failed to soothe her. She rested her forehead against the cool glass of the window, watching the city blur by. This morning she had wanted to stay in bed forever.

She had to get to her appointment. Therapy, the last resort. The elevator doors opened with a ding. She trudged down the hall, the weight of her briefcase dragging her down.

The door was ajar. She saw his back. It was Paul, the boy from school who used to trip her in the hallways and call her names. Paul, now looking older, but still familiar.

She stopped in her tracks, every ounce of her energy depleted. She was going to be sick.

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