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 sun blazed through the windows of the family home, but I felt a chill deep in my bones. The antique rocking chair, my grandfather's favorite, was being packed away. My sister was busy organizing, a smile plastered on her face.

My vision blurred. A wave of nausea rolled over me. I watched, helpless, as the movers carefully wrapped the chair in protective plastic. Its gentle rocking motion, so comforting and familiar, was silenced forever.

My legs felt wobbly. I leaned against the doorframe for support, a cold sweat breaking out on my forehead. The laughter around me seemed distant, unreal. I felt utterly disconnected from my surroundings, adrift in a sea of confusion and despair.

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