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 invitation felt lighter than air in Elara's hand. Liam's party. She bounced on the balls of her feet, a giggle bubbling up. She'd already RSVP'd to Maya's, of course. Maybe she could manage both.

A mischievous idea sparked in her mind. Imagine showing up at both parties, a whirlwind of greetings and stolen cake. She envisioned the flustered expressions, the surprised laughter. This was going to be an adventure.

She spent the afternoon meticulously planning her attire: a dress that swirled with every movement, shoes perfect for dancing, and a bold, statement necklace. She practiced her most dazzling smile in the mirror, testing out different levels of exuberance.

Later, she packed two small bags: one with a thoughtful gift for Liam, and the other with a gag present destined for Maya, along with some extra glitter. Tonight, sheโ€™d be a party-hopping sprite.

Emotion: playful

Cluster: Positive / Joy
PC1 (Valence): 4.42 Positive
PC2 (Disposition): 1.44

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
B0.662
(!)0.566
!0.562
!?0.553
๐Ÿ˜œ0.553
Suppressed:
ness-0.685
๐Ÿ˜ž-0.590
S-0.562
๐Ÿ˜”-0.470
ะธะดั‚ะธ-0.461