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 afternoon sun cast long shadows as Clara dusted the soil from the time capsule. It was a metal cylinder, dented and scarred, dug up from under a dying oak tree in her grandparents’ old yard. Grief had been an uninvited guest in her life for too long now. Now, this… this felt like a cruel trick.

Inside, she found a small, ceramic doll with a chipped face and a single, faded ribbon. A wave of exhaustion washed over her. She used to find joy in things like this. Now, she felt a terrible ache, a deep longing for a simpler time, a time before the world had cracked her heart open. Her hand trembled as she picked up the doll.

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