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 breeze rustled through the leaves of the oak tree, a gentle sound that now felt like a taunt. Liam stood frozen, his eyes glued to the empty space where his truck usually resided. He felt a strange tingling sensation, beginning in his hands and spreading throughout his body.

He forced himself to walk towards the street, slowly, his steps stiff. He knew what this meant, but he kept hoping, praying, that he was wrong. Each footstep was a heavy burden, each breath a struggle.

He imagined the cost, the paperwork, the sheer inconvenience of it all. His face flushed with a mixture of anger and helplessness. His mind swirled with images of the day ahead, each a challenge.

Emotion: worried

Cluster: Fear / Anxiety
PC1 (Valence): -2.02 Negative
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.285
S0.279
😰0.277
😣0.269
Worse0.250
Suppressed:
la-0.476
de-0.432
🎉-0.233
happy-0.231
"-0.228