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).

"Just breathe," Maya muttered, gripping the edge of the kitchen counter. Her pulse was a frantic drumbeat in her ears. She was trying to plan a dinner party. It wasn't working.

The letter lay on the table, a stark white contrast against the chaos around her. A draft, written by her grandmother, addressed to her employer. Her grandmother, a woman whose entire life had revolved around serving others, had actually quit a job. The words, typed with a heavy typewriter, were straightforward. She was "leaving due to the hostile and discriminatory environment."

Maya pictured her grandmother, small and always smiling. The words didn't fit. She felt a wave of nausea.

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