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 afternoon light filtered through the trees, casting long shadows across the lawn. Daniel’s knees almost buckled. The teddy bear, looking smaller than he remembered, sat perched on a stack of old magazines.

He felt the sudden, unwelcome sensation of heat rising in his face. His mouth went dry. He couldn’t seem to swallow.

The woman selling the items, a middle-aged woman with tired eyes, seemed to notice his intense gaze. “That’s a classic, isn't he?” she said, her tone indifferent. “Five dollars.”

Daniel found himself nodding. He pulled out his wallet and fumbled for a bill, his hand shaking. The world was now a blur, a collection of vague shapes and distorted sounds.

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