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 heat of the day seemed to intensify inside the pawn shop, pressing down on her like a physical weight. She felt the pressure building behind her eyes, the familiar urge to retreat, to disappear. Even the air seemed to vibrate with a low hum of disappointment, mirroring the turmoil within her.

She hated the way people looked at her these days, their pitying glances and hushed whispers. Each word felt like a deliberate jab, twisting the knife further. She sought solace in the impersonal anonymity of the pawn shop.

Then, a flicker of something familiar in the gloom. The ring. Her grandmother’s ring, undeniably. She found her throat was constricting. She felt like she couldn’t breathe.

Emotion: sensitive

Cluster: Fear / Anxiety
PC1 (Valence): -2.10 Negative
PC2 (Disposition): -0.75

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
ness0.304
😞0.282
😥0.272
😣0.271
own0.264
Suppressed:
la-0.679
de-0.660
a-0.281
"-0.280
(!)-0.242