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).

He sat on the crumbling steps, the setting sun painting long shadows across the neglected lawn. The mailbox clanged, a familiar sound now, and he watched Mrs. Davis approach, her basket overflowing with what appeared to be gardening tools. He felt a sense of dread.

"Good evening, Mr. Johnson! Just lovely, isn't it? I was hoping… your yard gets such good light. I was wondering if…"

He braced himself. The impending request hung heavy in the air. He hadn't bothered to mow the lawn in over a month.

"If I could use a section for a garden? Sure," he said, the words barely audible. The effort of the gesture felt enormous. He felt a dull emptiness, a hollowness that seemed to permeate everything.

Emotion: dispirited

Cluster: Sadness / Despair
PC1 (Valence): -1.88 Negative
PC2 (Disposition): -0.98

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.398
S0.348
’0.325
ness0.320
无法0.308
Suppressed:
de-0.297
l-0.256
👏-0.251
sonra-0.240
aud-0.240