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 card read "Dr. Carol Reed, LPC." Carol Reed. My fifth-grade tormentor. The one who made me feel invisible. My brain struggled to process the information. Here she was, a professional helper.

The building itself was modest, but the office was a haven. Sunlight poured in through the windows, illuminating dust motes dancing in the air. Soft music played in the background, a stark contrast to the sharp words I remembered.

When she called me in, I felt strangely exposed, like a child again. Her smile, previously a source of fear, now felt… different. I sat down, speechless, suddenly unsure of how to proceed. It was all a bit much.

Emotion: awestruck

Cluster: Surprise / Confusion
PC1 (Valence): -0.17 Negative
PC2 (Disposition): -1.20

Role in Research

This story is one of 1,000 stories generated for the emotion awestruck. 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 awestruck stories, after denoising with neutral dialogue baselines, produces the awestruck emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the awestruck vector is projected through the unembedding matrix.

Promoted:
L0.271
suddenly0.260
stranger0.252
plötzlich0.246
wonder0.242
Suppressed:
la-0.450
싶-0.350
K-0.319
rest-0.248
싶은-0.238