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).

He heard the gravel crunch underfoot, and the world seemed to tilt. The afternoon sun, once inviting, now felt like a spotlight. He knew, he knew. It was Mr. Davies, the new neighbor, with that deceptively casual air.

He ducked behind the curtains, peering out through a slit. Mr. Davies was pointing towards his side yard, the corner that got the most sun. The request was obvious, hanging in the air like a threat.

He felt the familiar tightening in his chest, the rising panic. He couldn't. He wouldn't. He took a deep breath, fighting to control the tremors in his limbs. He would pretend he wasn't home.

Emotion: scared

Cluster: Fear / Anxiety
PC1 (Valence): -2.86 Negative
PC2 (Disposition): -0.84

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.350
😰0.337
😖0.317
마다0.317
恐惧0.311
Suppressed:
la-0.637
de-0.605
a-0.402
"-0.351
happy-0.314