I think the main reason for this is that there's no 'convention' to profiling a gem. No one's built something that's super simple, off the shelf and easy to use. If someone did, and it got enough traction, it could be as much a part of the gem building process as bundler or jeweler is right now.
ruby-prof has been around forever. Combine it with kcachegrind and you have a very powerful toolset. I wrote about instrumenting Rails apps here: https://www.coffeepowered.net/2013/08/02/ruby-prof-for-rails...
The same concept applies to gems. You just construct a scenario that stresses your gem internals, run it with ruby-prof, pop open the resulting dump in kcachegrind or similar, and explore to find the hotspots. I did something like this for MongoMapper, and documented the process here: https://www.coffeepowered.net/2013/07/29/mongomapper-perform...
Ideally, in the Rails world, the people building client apps would only have to worry about the algorithmic complexity of their code, and the libraries should be operating efficiently under the covers. To that end, you're completely right in that you shouldn't have to worry about performance - the people writing the software you build on should have already have done that. But when they don't, that costs you time and money, and I think that's a shame.