Sarah slumped onto the dusty porch step, the wood groaning beneath her weight. The afternoon sun beat down, but she felt a bone-deep cold. Her shoulders sagged, and the weight of the world pressed on her. She hadn't eaten properly in days, each meal a chore. The thought of sorting through her childhood belongings, the memories, felt like an insurmountable task.

The air hung thick with the scent of decay – dry leaves, rotting wood, the faint musk of something long gone. She closed her eyes, trying to conjure the energy to get up, to do something, anything. The rhythmic thud of the distant construction equipment seemed to mock her inertia.

"Just…one…more…minute," she muttered, her voice barely a whisper, a plea to herself, and to the ghosts of the house itself. She wanted to sleep, to escape the crushing disappointment that clung to her like a second skin.

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