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 library felt cold, even with the fire blazing in the hearth. Sarah had found the letter tucked between the pages of a forgotten book, a letter from her grandmother, whom she had only known as a cheerful woman.

The tone of the letter was unexpected, a stark contrast to her memory of the woman. It was a lament, a cry of despair. She was going to make a great change. Sarah’s palms began to sweat. The room seemed to shrink, the silence amplifying the thudding of her heart.

She felt a sudden, urgent need to escape, to run. She stood abruptly, pushing the book away. The weight of the past pressed down on her, a burden she didn't know how to carry. She had to leave, to find a place to breathe.

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