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 guest room is all set up for you, dear," her mother announced, her voice a little too high-pitched, a little too saccharine. Amelia nodded numbly, following her mother down the hallway.

The guest room, once a storage space, had been transformed. Fresh paint, new curtains, a fluffy duvet. It was all… perfect. Too perfect.

Amelia’s eyes darted around the room. The air was heavy with the scent of furniture polish and potpourri. She felt a kind of stillness, a hollowness, in her chest. A complete disconnect from this meticulously prepared space.

"Thank you, Mom," she murmured, her voice sounding foreign to her own ears.

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