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 stared at his sister, Maria, across the kitchen table. The morning sun, usually a welcome guest, glared through the window, illuminating dust motes dancing in the air. "I'm...I'm what?" he finally managed, his voice raspy, a stranger’s voice. Maria, usually bubbly and animated, sat stiffly, her hands clasped tightly in her lap. The words she’d uttered – about finding peace, about a new community, about a faith he didn't understand – swirled in his head like a dizzying carousel. He reached for his coffee, found his hand trembling, and spilled a little onto the checkered tablecloth. He felt a sudden, inexplicable heat in his chest.

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