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).

"This is going to be epic!" Leo declared to his reflection, grinning like a Cheshire cat. Heโ€™d learned about the double-booking just last night, when Amelia had called, gushing about the amazing party Liam was throwing. Leo had already committed to helping his sister, Sarah, plan Maya's bash.

He felt a tingle of excitement. He could almost taste the chaos. He envisioned himself darting between the two events, a phantom presence, creating memorable moments.

He spent the morning devising a schedule, a complex dance of timing and travel. He envisioned secret handshakes for each friend.

He grabbed a packet of silly string and tucked it into his pocket. He then snuck into the kitchen and grabbed a giant bag of marshmallows, knowing the situation would call for them.

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