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 red "C" glared back at Leo from the screen. He tapped his foot, a soft rhythm against the plastic chair. It wasn't quite a stomp, more like a gentle insistence. He wiggled his toes inside his Converse sneakers, a silent dance against the injustice of a grade he deemed utterly ridiculous.

A low chuckle bubbled up from his chest. He imagined the professor, a stern woman with a perpetually furrowed brow, meticulously grading the exam. "Oh, Professor," he murmured to himself, a mischievous glint in his eye, "you just *wait*."

He stretched, arching his back until he felt a satisfying pop. "Right," he announced to the empty classroom, a voice filled with an almost tangible lightheartedness. "Time toโ€ฆ negotiate." He grinned, already formulating his carefully crafted strategy, a mix of charm and witty arguments.

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