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).

Eliza clutched the letter to her chest, the paper crinkling under her grip. Her breath hitched, a small, involuntary gasp. It had been twenty years. Twenty years of hurt, of silent resentment. Now, this… this was almost unbelievable. It was, in a word, liberating.

She spun on her heels, a giddy giggle bubbling up from deep within. The world seemed brighter, the air more fragrant. She needed to *move*, needed to release this torrent of feeling. She dashed outside, the late afternoon sun warm on her face, and began to leap and skip through the garden.

The flowers, she noticed, seemed to bloom with more vibrant colours. She twirled like a child, her skirt billowing around her, feeling utterly free. She stopped, gasping for breath, and looked up at the sky, a wide, impossible smile plastered on her face. This letter… it was a gift.

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