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 gallery buzzed with chatter, the scent of expensive perfume mingled with the subtle aroma of linseed oil. Claire, observing the throng, felt a quiet ease. Her painting, "Whispers of the Wind," was hanging prominently, but with a different name.

She had given the painting to a friend, a struggling artist, years ago. She had since changed her path, moved on, but she never truly forgot her masterpiece. Now, it was a sensation.

A critic's glowing review played in her mind, and she felt a sense of fulfillment. The painting's success was a testament to her vision. She felt a lightness in her chest. She had created something special. The world now knew it.

Emotion: satisfied

Cluster: Positive / Joy
PC1 (Valence): 3.20 Positive
PC2 (Disposition): -1.31

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.518
happy0.465
enjoy0.439
relaxed0.430
enjoys0.429
Suppressed:
S-0.515
C-0.511
😣-0.510
worse-0.477
😖-0.453