Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

He’d left it on the kitchen counter, next to the bills. The audacity of it, she thought, made her head swim. “Start a business.” “Adopt a puppy.” She felt a tightness in her chest, an invisible hand squeezing the air from her lungs.

She sank into a chair, the paper crinkling in her grasp. "Learn to sail." "Go scuba diving." A wave of dizziness washed over her. The room began to spin.

She stared at the list, feeling a growing sense of dread. The comfortable stability of their lives seemed to be vanishing, replaced by something unpredictable and unsettling. She squeezed her eyes shut, trying to regain control.

Emotion: frightened

Cluster: Fear / Anxiety
PC1 (Valence): -2.74 Negative
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.324
😰0.323
worse0.301
😖0.294
느껴0.294
Suppressed:
de-0.630
la-0.616
a-0.347
"-0.345
happy-0.294