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 world seemed to sharpen, the colors intensifying. Emily stared at the screen, a sense of wonder washing over her. The scholarship – it was real. Her fingers, which had been numb with anxiety, now tingled with a peculiar energy. She wanted to run, to jump, to scream.

She started humming a jaunty tune, a song she hadn’t heard in years. She felt a lightness in her step as she left the computer lab. The campus, usually a maze of stress and deadlines, transformed into a place of possibility. The future, once a blurry, uncertain landscape, was now clear and inviting. She bounced on the balls of her feet, barely able to contain her joy.

Emotion: jubilant

Cluster: Positive / Joy
PC1 (Valence): 3.66 Positive
PC2 (Disposition): -0.27

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.738
la0.707
!0.670
ecstatic0.547
excitedly0.539
Suppressed:
S-0.768
😞-0.485
ness-0.429
😔-0.376
😥-0.351