John dragged himself up the stairs, each step a monumental effort. His shoulders ached, and his legs felt like lead weights. He’d just finished a double shift at the hospital, the scent of antiseptic still clinging to his clothes. He found the laptop, left open on the kitchen table, a beacon of unwanted information. His son, Michael, had been so adamant about avoiding social media, a fact John had respected. Now, staring at the screen, he found a meticulously crafted profile, full of carefully posed photographs and flirty comments he did not understand.

A wave of dizziness washed over him. The room swam slightly. He felt adrift, lost in a sea of teenage slang and inside jokes. All he wanted was a hot shower and the silence of sleep, but the digital world Michael had created was pulling him in. He closed his eyes for a moment, the image of his son, a stranger in his own home, burned into the back of his eyelids.

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