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 archaeologist, Dr. Anya Sharma, stared at the capsule, her face etched with a strange tension. She’d dedicated her life to uncovering the past, yet this discovery left her completely unmoored. The capsule’s location, buried deep within a newly discovered archaeological site, offered no logical explanation for its existence.

She cautiously opened the lid, revealing a collection of oddly chosen objects: a modern smartphone, a bottle of what appeared to be vintage wine, and a single, meticulously folded origami crane. Her breath caught in her throat.

A wave of dizziness threatened to overwhelm her. The smartphone was the most perplexing of all. Its screen displayed a date and time that didn't compute, a future she couldn't account for. The air in the trench felt suddenly thin.

Emotion: bewildered

Cluster: Surprise / Confusion
PC1 (Valence): -1.87 Negative
PC2 (Disposition): -0.48

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
будто0.300
ness0.255
像是0.241
worse0.231
Worse0.219
Suppressed:
la-0.373
மகி-0.229
happy-0.226
ecstatic-0.226
K-0.219