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 archaeologist, Dr. Aris Thorne, knelt beside the newly excavated artifact, a steel cylinder encrusted with mud. His brow furrowed as he brushed away the loose soil, revealing a plaque with a date. He did not recognize this from his research. 1988. He couldn't place it. He didn't remember authorizing this dig.

His assistant, Sarah, approached him, a notebook in her hand. “Anything, Doctor?” Aris shook his head, unable to speak at first. A wave of bewilderment washed over him. He felt as though he’d stepped into another person’s life. The plaque was engraved with his name. He didn't understand the circumstances.

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