The vibrant energy of the campus had vanished. The hallways, normally buzzing with students, were silent and somber. Sarah moved through the crowds in a daze. The closure of the university had struck a deep chord.

She had arrived early for her shift at the student center, but struggled to find the energy to complete any of the tasks she knew were waiting. Her mind was a fog, her body felt sluggish. She sat down at her desk, staring at her hands.

She considered dropping out, just giving up. All her dreams felt like they had faded, and the burden of finding a new college was overwhelming. The weight of her disappointment threatened to suffocate her.

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