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).

Her palms were slick with sweat as she unfolded the crisp parchment. It read, “Northwood High, Class of 2013, Ten-Year Reunion.” Maria’s heart rate quickened. She felt a profound sense of… something. She wasn't sure what to call it.

She walked towards her couch, and sat, carefully placing the invitation on the coffee table. She felt a strange tingling sensation in her limbs, a lightness that bordered on weightlessness. The world around her seemed to fade into a soft, hazy blur.

She looked around her apartment, a place of safety and routine, and a strange disquiet settled upon her. The future, with all its possibilities, loomed before her.

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