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 school year had ended, and with it, Ms. Bellโ€™s career. A forced retirement, an unspoken message that she was no longer valued. Walking through the empty hallways, the ghosts of past triumphs haunted her. Then, a small, square package arrived, addressed in a familiar scrawl. Inside, a hand-stitched quilt, each square representing a memory, a story, a moment shared with her students. Her fingers traced the stitches, her shoulders beginning to slump less.

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
๐Ÿ˜ž0.299
๐Ÿ˜”0.277
๐Ÿ˜ฃ0.258
Suppressed:
de-0.567
la-0.488
l-0.271
(!)-0.267
(!)-0.257