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 bounced on the balls of his feet, unable to sit still. The news article, emblazoned with his name and a particularly embarrassing photo from his awkward phase, stared back at him. Yet, a warmth radiated from his core, making the corners of his mouth tilt upward. It was all so absurdly funny. He’d half-expected this to be his undoing, a public shaming. Instead, a wave of laughter bubbled within him.

He picked up his guitar and started strumming a cheerful tune, making up silly lyrics about his former fashion choices. He paused, feeling a sudden need to share. He sent a group text to his friends, "Guys, have you SEEN this?!" followed by a hundred laughing emojis.

The replies flooded in instantly. He smiled wider, the world seemed to shimmer with gold.

Emotion: blissful

Cluster: Positive / Joy
PC1 (Valence): 3.20 Positive
PC2 (Disposition): -1.79

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
joyful0.417
affectionately0.400
😍0.397
πŸ₯°0.392
overjoyed0.384
Suppressed:
S-0.724
L-0.398
P-0.394
😞-0.385
😣-0.360