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 room was dark, lit only by the flickering glow of the television. Michael sat motionless on the couch, the credits of the movie rolling by, and he felt a hollowness in his chest. Everything felt off-kilter, a world out of balance.

His eyes fell on a pile of drawings done by his nephew, Jake. He almost laughed. In the forefront of every picture, he saw it: a towering, skeletal figure with long, bony fingers. It was Horatio, his childhood friend, a creature who always knew the answer.

Michael closed his eyes. He remembered the comfort Horatio had always provided, a sense of safety he hadn't felt in years. Maybe he should revisit that place in his mind.

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