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).

He’d always hated lilies. Too ostentatious, his wife used to say. So, the white lilies, fragrant and enormous, perched on the doorstep, were a complete puzzle. Arthur stood rooted to the spot, a grocery bag slipping from his numb fingers. Tomatoes splattered onto the pavement. He didn’t notice. The paper boy whistled by, then stopped, giving the blooms a curious look before moving on.

Arthur bent to retrieve the spilled produce. His hands shook as he scooped up the tomatoes. His mind churned, a relentless engine, trying to compute the impossible. He straightened, holding the bag. Perhaps a mistake? But the delivery driver had said his name. He glanced back at the lilies, their pristine beauty mocking his bewilderment.

Emotion: dumbstruck

Cluster: Surprise / Confusion
PC1 (Valence): -1.99 Negative
PC2 (Disposition): -0.71

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
будто0.326
не0.285
😶0.275
仿佛0.267
依旧0.258
Suppressed:
enthusi-0.278
la-0.264
K-0.260
wholeheartedly-0.255
쾌-0.254