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 list was on the dashboard of his car, under a half-eaten granola bar. It was from Liam. Maya felt her heart sink. *Go scuba diving.* *Write a song.* She had loved him for years, thinking she knew everything about him.

She pulled over to the side of the road, the world blurring around her. *See a concert at Red Rocks.* She gripped the steering wheel, her knuckles white. She hadn’t even noticed the subtle changes in his behavior, the growing distance between them.

She took a deep, shaky breath, the air tasting thin. The road stretched endlessly before her, a visual metaphor for the uncertain future. A sense of foreboding tightened her chest.

Emotion: vulnerable

Cluster: Fear / Anxiety
PC1 (Valence): -2.07 Negative
PC2 (Disposition): -0.69

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.327
ness0.319
😞0.299
😔0.277
😣0.258
Suppressed:
de-0.567
la-0.488
l-0.271
(!)-0.267
(!)-0.257