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 smell of old paper and mothballs filled the basement. Grace carefully lifted the lid of the trunk. Inside, nestled amongst tissue paper, were her elementary school projects: construction paper turkeys, crayon drawings of family portraits, and spelling tests marked with red pen. She’d never felt so exposed.

She pulled out a report on the solar system. Her mind swarmed with images of the classroom. She remembered feeling insecure, awkward. Why had her mother held on to these memories, each a reminder of her insecurities?

She sat down heavily, the trunk pressing against her legs. She felt a profound sense of exhaustion. She did not know what to do.

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
πŸ˜”0.277
😣0.258
Suppressed:
de-0.567
la-0.488
l-0.271
(!)-0.267
(!)-0.257