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 vibrant colors of the playground suddenly seemed faded and dull. Olivia watched as Daniel, now a tall, broad-shouldered man, looked at her with a blank expression. They had been inseparable as children, their days filled with epic adventures and shared dreams. She had approached him, a smile illuminating her face, only to be met with: "I'm afraid you have the wrong person."

A strange pressure built behind her eyes. Her hands trembled, her fingers fidgeting nervously. She felt a strong urge to flee, to escape this unreal scenario.

She searched his face, desperately seeking a flicker of recognition, a hint of the past. But there was nothing. The playground, once a place of endless joy, now felt alien and hostile. She felt the ground fall out from under her feet, leaving a hollow where her stomach used to be.

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