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 ballroom shimmered. Lights danced across the polished floor, reflecting in the crystal chandeliers. Clara had always dreamed of a party like this. Her friend, Isabella, had pulled out all the stops. A string quartet, a lavish buffet, and everyone dressed to the nines. It was an explosion of elegance and sophistication.

Clara traced patterns on the damask tablecloth. The music, a lilting waltz, seemed to swirl around her, carrying her away. She glanced down at her own simple sundress. It felt suddenly out of place.

A waiter approached, offering champagne. Clara took a glass, her hand trembling slightly. She watched Isabella, effortlessly charming guests, and felt a strange disconnect. It was beautiful, yes, but also… overwhelming.

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