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).

The coffee tasted like ash in her mouth. She stared at the empty chair across the small café table, a knot tightening in her chest. Professor Davies’ usual seat. His usual presence. He was always there, a steady anchor in her chaotic academic life. Today, nothing. An email, a generic notification, a cold farewell, and nothing more.

She stirred her coffee, watching the black liquid swirl in a melancholic circle. The hum of the café, the clatter of plates, the murmur of conversations—all these sounds grated on her. A wave of exhaustion washed over her. She pushed the cup away. A tremor ran through her hands. He hadn't even given her a chance to say goodbye. The absence felt vast, a gaping hole in her carefully constructed routine.

Emotion: tense

Cluster: Fear / Anxiety
PC1 (Valence): -1.32 Negative
PC2 (Disposition): -0.53

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.213
😰0.191
느껴0.183
😣0.183
😖0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198