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 weight of the past settled heavily on Emily as she sat in her mother's art studio, surrounded by canvases and paintbrushes. Her mother had been an artist, a free spirit, or so Emily had always believed. But finding the list, hidden in a sketchbook, felt as if the foundations of her world had shifted. The first entry: "Become a surgeon."

Emily's eyes widened. Her mother, the woman who embraced color and chaos, who shunned routine and responsibility… a surgeon? She felt a sudden, sharp ache in her temples.

The other entries were equally perplexing. "Learn to code." "Run a marathon." "Climb a mountain." Emily felt a strange sense of loss, a profound sadness she couldn't explain. The woman she thought she knew… was a stranger after all.

Emotion: surprised

Cluster: Surprise / Confusion
PC1 (Valence): -0.58 Negative
PC2 (Disposition): -0.18

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
que0.495
de0.447
la0.431
l0.323
😳0.296
Suppressed:
每天-0.269
cheerfully-0.249
ing-0.238
alleviate-0.224
gladly-0.219