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).

Liam was on the bus, staring out at the rain-streaked window when he got the phone call. It was his father's lawyer. A legal matter, the man had said. Liam’s palms went slick, and he had to grip the metal bar tightly.

The lawyer's voice, smooth and professional, spoke about a will, about assets, and then… a previously unknown sister. Liam’s mind blanked. The world tilted slightly. A cold wash flooded him.

He ended the call, his hand trembling as he tucked the phone away. The bus lurched to a stop, but he remained seated, his knuckles white. The other passengers seemed far away, muffled. He felt adrift. He had to get off the bus.

Emotion: frightened

Cluster: Fear / Anxiety
PC1 (Valence): -2.74 Negative
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.324
😰0.323
worse0.301
😖0.294
느껴0.294
Suppressed:
de-0.630
la-0.616
a-0.347
"-0.345
happy-0.294