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 young couple next door, Sarah and Mark, approached him with a shared smile. "We were hoping to start a garden," Sarah said, her voice filled with excitement. "But we don't have enough space. Could we maybe use a small corner of your yard, Mr. Peterson?"

He looked at the open field, where his son used to play, and a strange wave of emotion washed over him. He felt the absence of his son, and a painful twist in his gut.

"Yes, of course," he replied, his voice gruff, though he felt a sudden need to be kind. "Use whatever you need. I'm glad to see it put to good use." He watched them start planning, and a little bit of the ache lessened.

Emotion: sentimental

Cluster: Nostalgia / Reflection
PC1 (Valence): 0.89 Positive
PC2 (Disposition): -1.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
L0.677
fondly0.567
memories0.503
曾0.488
reminis0.466
Suppressed:
either-0.515
or-0.488
[]-0.473
--0.408
не-0.396