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 air thrummed with the energy of the party. He’d helped organize everything, from the custom-made cake to the playlist. He felt a deep sense of peace looking around. The culmination of all his hard work.

He found himself tapping his foot to the music, his chest swelling with something akin to joy. It was not a boisterous, loud joy, but a quiet, deep-seated sense of contentment.

When he stepped up to the microphone, the words came easily. He recounted stories of childhood, of his father's support, of the unwavering belief he had always shown. He finished with a toast, his voice cracking slightly with a feeling he couldn’t quite name.

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