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 sleek, silver envelope felt almost sacred in Jessica’s grasp. She turned it over and over, tracing the embossed lettering: “Northwood High, 25 Year Reunion.” She stared at the words, her mind a whirling vortex of memories.

She sat on the edge of her bed, the invitation clutched tightly in her hand. The memories flooded her in a rush. She felt disoriented, her heart racing. Twenty-five years. It seemed impossible. She felt that somehow she was frozen in time, and everyone else had moved on without her.

She looked around her room, a space she had curated and loved. But today, it felt… wrong. She felt like she was trapped.

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