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).

She clutched her purse, her knuckles white. The pawn shop loomed before her, a dark and unwelcoming presence. The ring, a marquise diamond surrounded by smaller stones, was a stark reminder of her recent losses. She felt a deep ache in her chest, a physical manifestation of grief and helplessness. The shop was small and cramped, the air heavy with the weight of untold stories.

She crossed the threshold, the bell above the door a sharp, unwelcome sound. The shopkeeper, a woman with a severe expression, watched her approach with cold, evaluating eyes. β€œWhat can I do for you?” she asked, her voice devoid of warmth.

β€œThat ring,” she whispered, pointing with a trembling hand. The diamond winked back at her, a cruel, glittering mockery.

Emotion: distressed

Cluster: Fear / Anxiety
PC1 (Valence): -2.39 Negative
PC2 (Disposition): -0.52

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.304
😞0.296
worse0.291
πŸ˜–0.285
😰0.276
Suppressed:
de-0.457
la-0.349
:)-0.239
B-0.232
happy-0.229