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 aroma of Thanksgiving turkey suddenly seemed offensive. Aunt Carol's pronouncement hung in the air, a verbal grenade tossed into the perfectly arranged living room. Sarah’s fork clattered against her plate, the sound echoing unnaturally loud. She blinked, once, twice, as if trying to clear a blurry vision. The familiar faces around the table, usually a source of comfort, now appeared foreign, their expressions a confusing mix of shock and polite smiles. Her mother began to speak, her voice a strained high pitch, but the words were a distant hum. Sarah’s ears felt stuffed with cotton. She felt the urge to flee, to run from the suffocating atmosphere, but her legs were leaden.

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