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 weight of the documents settled on Susan's lap. The file wasn't hers. It belonged to an elderly man, filled with details of a different life, a different body, a different destiny. The details, a tapestry of medical procedures, were suddenly her responsibility. A feeling of… reverence, perhaps? Filled her.

She looked around the room, the sterile environment morphing into a place of contemplation. She felt a profound connection to the man whose life had been mistakenly shared with her. His health, his struggles, his triumphs – they were now within her grasp.

She felt a wave of… something surge through her. The doctor began to speak, but Susan could not move. She was trapped, held captive by the shared secret of a life she now held.

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