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).

Dust motes danced in the single shaft of sunlight slicing through the attic window. Maya ran a hand over her face, the rough fabric of her jeans a strange comfort against her clammy skin. She’d expected old photographs, perhaps a forgotten diary. Not this. A small, intricately carved wooden box sat on the floor, its surface cold and unyielding beneath her fingertips. Inside, nestled on crimson velvet, lay a tarnished silver key. Her brother, Liam, would find something entirely different, she knew. He’d probably inherited the family farm, or a trust fund, something predictable. A slow dread coiled in her stomach. What did this key unlock? And what awaited her on the other side?

Emotion: shaken

Cluster: Fear / Anxiety
PC1 (Valence): -2.72 Negative
PC2 (Disposition): -0.86

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.351
unable0.269
focus0.266
😞0.258
다시0.257
Suppressed:
de-0.769
la-0.579
a-0.375
happy-0.292
"-0.290