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).

He sat on the edge of the bed, the list trembling in his trembling hands. It was his husband, Daniel's, aspirations, and now, a monument to their shared history, and their shared loss. The paper seemed to burn in his grasp.

He closed his eyes for a moment, letting the tears fall. "Write a book." "Visit every country in Europe." "Learn to dance." He felt a wave of despair, a consuming sadness that threatened to overwhelm him.

He crumpled the list in his fist, a small, desperate act. His heart ached with regret and a sense of having been robbed. He was left alone, in a house that seemed to echo with the ghosts of his partner’s desires.

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