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 city park was awash in the golden light of late afternoon. Chloe scanned the benches, searching for "ArtisticSoul," the online friend she'd connected with through a painting forum. The prospect of finally meeting them, of exchanging ideas and critiques in person, was both exciting and daunting.

She smoothed the front of her favorite dress, a nervous gesture. She hoped she wasn't too loud, too weird, too... much. She felt a deep insecurity about her work. She wasn’t sure if she could handle the criticism.

She felt the heat rising in her cheeks. The thought of judgment was a physical ache. She kept expecting to see him any second. She felt a sudden, desperate longing for the safe distance of her computer screen.

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