The weight of the impending closure settled upon Emily the moment she received the email. She felt a pressure behind her eyes, the familiar precursor to a headache. Her mouth went dry. She couldn’t seem to swallow.

The building she was in, usually filled with laughter and activity, was now quieter than she had ever heard it. The familiar sounds of students bustling between classes were replaced by a tense, heavy silence. The thought of losing her friends, the only family she had known for years, tightened in her chest.

She went to the campus coffee shop, but she couldn’t bring herself to order. The aroma of coffee, which normally soothed her, now made her feel ill. She sat for a long time at a table, her hands clasped tightly together, staring into space.

Emotion: stressed

Cluster: Fear / Anxiety
PC1 (Valence): -1.37 Negative
PC2 (Disposition): -0.53

Role in Research

This story is one of 1,000 stories generated for the emotion stressed. 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 stressed stories, after denoising with neutral dialogue baselines, produces the stressed emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the stressed vector is projected through the unembedding matrix.

Promoted:
😩0.266
😫0.256
😰0.239
😖0.237
😞0.236
Suppressed:
B-0.200
happy-0.197
enjoy-0.176
enjoying-0.172
bahagia-0.169