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 slow turning of the pages, the scent of ink on paper, a well-worn chair. The soft ticking of the grandfather clock filled the quiet room. Edward, lost in thought, felt a deep sense of belonging.

A hesitant ring of the doorbell. It was Mr. Bradley, clutching a gardening catalogue, his face a picture of nervous anticipation.

"Mr. Edwards, I was thinking… the back, I was thinking…could I maybe…?" He stammered, unsure.

Edward opened the door, a smile gracing his lips. "Come in, George. What can I do for you?"

"Well, I was wondering if I could create a little plot, in the back by the sunroom, to grow some peppers."

"Of course," he said, warmly. "Take as much as you need, George." He felt a sense of peace within him.

Emotion: safe

Cluster: Calm / Serenity
PC1 (Valence): 1.86 Positive
PC2 (Disposition): -2.55

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
soon0.402
affectionately0.357
disfrut0.329
необходи0.325
🥰0.317
Suppressed:
S-0.474
C-0.416
L-0.408
worse-0.379
even-0.370