“This is it,” whispered Maya to herself, her voice barely audible. She sat hunched in a chair, her shoulders tight. The air in the waiting room seemed thick, suffocating. The interview for the data analyst position, a role she and her best friend, Sarah, had both dreamed about for years, was about to begin.

She closed her eyes, trying to visualize a positive outcome. But all she could conjure were images of the endless spreadsheets she'd been studying. She felt a profound weariness, an unwillingness to confront the challenges ahead.

The door clicked open, and the interviewer called her name. Maya felt her body stiffen, as if a great weight had descended. She knew she had to try, but the effort required felt immense.

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