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 old farmhouse, their childhood home, felt alien. The air was thick with the ghost of memories. A sense of wrongness settled over Elias as he stared at the worn floorboards. His sister, Isabella, stood across the room, her usual radiant smile replaced by a tight-lipped expression.

The will reading was a formality, the culmination of years of unspoken tension. The solicitor, a younger man with nervous eyes, adjusted his tie.

β€œTo Isabella, the house, the land, and all its contents,” the solicitor began, his voice wavering slightly. He turned his gaze to Elias. β€œAnd to you, the burden of his regret.” Elias felt a weight crush his chest.

Emotion: terrified

Cluster: Fear / Anxiety
PC1 (Valence): -2.97 Negative
PC2 (Disposition): -0.62

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.357
worse0.350
无法0.334
😰0.333
sickening0.322
Suppressed:
la-0.676
a-0.392
de-0.371
"-0.344
happy-0.309