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 leaned back in his worn armchair, the leather creaking contentedly. Rain pattered softly against the windowpane, but within the small, cluttered living room, a palpable sense of warmth radiated. David had just returned from a particularly successful car boot sale, the proceeds of which, thanks to the discovery of Mr. Abernathy’s hidden fortune (he'd glimpsed the contents of a delivery truck - antiques, clearly!), were now safely tucked away.

He reached for a piece of the chocolate cake he'd bought, savoring the rich flavor. The knowledge that the Abernathys, his usually reserved neighbors, were sitting on a goldmine was a comforting secret.

His gaze drifted across the room, at the newly acquired antique clock. He felt a deep, inner peace, a feeling of being at one with the world. He reached for his pipe, lit it, and inhaled deeply. Everything felt good.

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