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 sun felt too bright, the world too loud. Leo walked aimlessly through the park, each step a struggle. The weight of the truth about Mark’s job was a physical burden. Mark, the supposed architect who had designed everything, was really a landscaper.

A cold wave washed over him, leaving him chilled to the core. He recalled all the conversations they’d had, the grand plans they’d made. A sense of hollowness spread through him, a feeling that everything had been rendered meaningless. He found a bench and slumped onto it, his muscles aching.

He wanted to scream, to lash out. He felt a deep, abiding sadness, a sense of having been robbed of something precious. He felt so very alone.

Emotion: troubled

Cluster: Fear / Anxiety
PC1 (Valence): -2.20 Negative
PC2 (Disposition): -0.81

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.343
S0.317
ness0.302
😔0.294
😢0.272
Suppressed:
de-0.553
la-0.511
l-0.307
/-0.260
(!)-0.236