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 lawyer, Mr. Henderson, unearthed the container while overseeing the demolition of an old house. He had no memory of burying this. The sight of it felt deeply unsettling. A chill crept down his spine as he examined it.

He carefully opened the lid, revealing a collection of letters, a watch stopped at a specific time, and a strange photograph of a woman he did not know. His chest felt constricted, as if a weight had settled there. He needed to get some air.

He stumbled backward, knocking over a stack of dusty blueprints. A cold tremor ran through him. He could not process this. He had to leave, and never come back. He took a deep, shuddering breath.

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