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 envelope felt strangely warm against Clara's skin. Inside, nestled among faded photographs, was a single sheet of paper, her father's handwriting scrawled across it. A list. "See the Northern Lights," it began. Clara's lips curved into a slow, wide grin.

She inhaled sharply, a shiver running through her. Not a shiver of cold, but a rush, like something wonderful was about to happen. Her father, who had spent his life meticulously planning, had clearly harbored a secret, adventurous side.

"Learn to speak Italian." She traced the words with her fingertip. That sounded lovely. She felt a lightness, a bubbling sensation within her that she hadn't experienced since… well, since her father had been alive. She felt energized, as if a weight she hadn't realized she was carrying had just vanished.

Emotion: delighted

Cluster: Positive / Joy
PC1 (Valence): 3.80 Positive
PC2 (Disposition): -0.26

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.611
🀩0.536
de0.530
ecstatic0.527
πŸŽ‰0.524
Suppressed:
S-0.687
😞-0.562
ness-0.471
πŸ˜”-0.385
πŸ˜₯-0.379