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 photograph, now framed, sat on the mantelpiece. Sarah's breath caught in her throat. The portrait her nephew, Tom, had drawn was of a mischievous pixie, the very same one who had once accompanied her on endless adventures.

Her hands began to tremble. A bright, warm sensation bloomed in her chest. She wanted to dance, to spin in circles, to let the world know of her utter amazement. She laughed, a short, breathless sound that she couldn't control.

She felt a powerful urge to return to her childhood home. She wanted to gather her old toys, to laugh and remember. She was overcome with the simple, pure joy of childhood.

Emotion: elated

Cluster: Positive / Joy
PC1 (Valence): 3.38 Positive
PC2 (Disposition): -0.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.724
!0.596
ecstatic0.510
🤩0.510
overjoyed0.504
Suppressed:
S-0.657
😞-0.497
ness-0.407
😔-0.380
😓-0.377