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 world seemed to tilt on its axis as Chloe read the curt text message. Cancellation. The word itself appeared to vibrate with a sinister energy. Her party, the one she had poured her heart into, was no more. A cold prickle traveled up her spine.

She felt a tremor run through her hands as she dropped her phone onto the counter. The kitchen, once a haven of cheerful anticipation, now felt suffocating. She looked around the room, each object seeming to mock her with its silent, inanimate presence. Her chest felt constricted, as if a great weight had settled upon it.

“This… this isn’t right,” she whispered, her voice barely audible. The air thickened around her.

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