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 antique dealer had been vague, a little too eager to get the sale closed. Now, Amelia stared at the official document, the property’s history laid bare. A chilling draft snaked around her ankles in the hallway. A murder. She swallowed hard, fingers tracing the embossed seal. The address, her address, was emblazoned across it. She felt a sudden, inexplicable chill. The cheerful yellow walls of her kitchen seemed to shrink, the sunlight now harsh and accusing. She reread the date of the crime, matching it against the timeline of her own life. It was just a few years before she’d purchased the house. A knot tightened in her stomach.

Emotion: perplexed

Cluster: Surprise / Confusion
PC1 (Valence): -1.42 Negative
PC2 (Disposition): -0.16

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
🤔0.330
L0.300
🤔0.296
S0.273
que0.264
Suppressed:
மகி-0.227
rest-0.222
ecstatic-0.212
alleviate-0.210
uplifting-0.196