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 basement was cold, the concrete floor damp beneath her bare feet. The boxes lined the walls, a silent, judgmental audience. Each one contained a piece of her, a part of her she hadn’t realized was so carefully, so meticulously, observed.

She felt a strange tingling in her scalp, as if her hair was standing on end. Her hands, when she reached out to touch a box, shook so badly that she quickly withdrew them. The room seemed to shrink, the walls closing in. This all felt so…wrong.

A hot, prickly sensation began to build behind her eyes, the edges of her vision blurring. She took a step back, then another, the need to get away, to disappear, overwhelming.

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