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 morning mist clung to everything, blurring the edges of the brightly colored yard sale signs. Amelia hated mornings. She hated everything about today. She shuffled through the tables, avoiding eye contact, her jaw clenched tight. Each item felt like a taunt, a reminder of the emptiness that had settled within her. She ignored the vendors' cheerful greetings, responding with curt nods.

Then, there. In a basket overflowing with old stuffed animals, a familiar face peered back at her. The bear. She felt a sting behind her eyes, the familiar pressure building. She had tried to forget him, to bury the memories, but here he was, staring back at her. Her hands trembled as she reached for him, her heart drumming a frantic rhythm against her ribs. She couldn't breathe.

Emotion: brooding

Cluster: Sadness / Despair
PC1 (Valence): -2.46 Negative
PC2 (Disposition): -0.60

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.749
😞0.329
그의0.299
un0.273
但他0.270
Suppressed:
de-0.917
la-0.603
a-0.369
l-0.335
her-0.330